{
  "schema": "crovia.sonar.provenance_scan.v1",
  "scanned_at": "2026-07-15T02:25:25.506411Z",
  "models_scanned": 500,
  "summary": {
    "with_training_section": 125,
    "with_declared_datasets": 107,
    "with_base_model": 110,
    "with_license": 284,
    "avg_provenance_score": 0.238
  },
  "chains": [
    {
      "model_id": "bigcode/astraios-3b-ia3",
      "scanned_at": "2026-07-15T02:00:01.452001Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "9baeedc34aad1780c543f1a75064412955ab31fe801182f3a1f2a4d0f4f3c9b7"
    },
    {
      "model_id": "bigcode/astraios-3b-lora",
      "scanned_at": "2026-07-15T02:00:04.241370Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "65ac44e278cc29eaa09082e97e304a94446daa56e2d97c1669710e3667908d39"
    },
    {
      "model_id": "bigcode/astraios-3b-parallel",
      "scanned_at": "2026-07-15T02:00:06.995014Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "ca431419e6b414f0f459efb685f07fcd077f9d9111cd742819bd7be5950adf1d"
    },
    {
      "model_id": "bigcode/astraios-3b-ptuning",
      "scanned_at": "2026-07-15T02:00:10.022621Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "98fcb7e628a7caf533eb690ece0008ac56c419d17790747755deba5a39da4e4f"
    },
    {
      "model_id": "bigcode/astraios-7b-adapterh",
      "scanned_at": "2026-07-15T02:00:12.792255Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "5f2bf0563379e5474af2ca9f1aacb2a09e0beb4f5cf47264e8b8b46e3603da21"
    },
    {
      "model_id": "bigcode/astraios-7b-adapterp",
      "scanned_at": "2026-07-15T02:00:15.578565Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "ad59ab6a020bcee5b06468fd31da6abbc3dbc9894683e9ee8d3024d67dc0fe84"
    },
    {
      "model_id": "bigcode/astraios-7b-fft",
      "scanned_at": "2026-07-15T02:00:18.339988Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/fsx/armel/issues/checkpoints-fft-7b/checkpoint-200",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /fsx/armel/issues/checkpoints-fft-7b/checkpoint-200"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "519d73577fec0b04bbbdfc2c8a0372aac68b4245a95a65b2c4c09c87ce8cfbd8"
    },
    {
      "model_id": "bigcode/astraios-7b-ia3",
      "scanned_at": "2026-07-15T02:00:21.092678Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "b6db66136f2ed6c5c2c8e4bc37d57823a294630ff4f715bb09c0ec774c25df48"
    },
    {
      "model_id": "bigcode/astraios-7b-lora",
      "scanned_at": "2026-07-15T02:00:23.845598Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "7b5b55aee1d1149740f4615e290b17151398dd42e353d997b4a0644aad7dadcc"
    },
    {
      "model_id": "bigcode/astraios-7b-parallel",
      "scanned_at": "2026-07-15T02:00:26.696981Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "4778b5d384dcdade8e12e85362cb68d789578428d383f449becf4f1a3519176d"
    },
    {
      "model_id": "bigcode/astraios-7b-ptuning",
      "scanned_at": "2026-07-15T02:00:29.504659Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "eaa14a420f1772510f93eab2a2d602c6afc2bdb82467b4f74508cba117a6ae8e"
    },
    {
      "model_id": "bigcode/astraios-adapterh",
      "scanned_at": "2026-07-15T02:00:32.360875Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "9f5f1706c891248f472d76b79f59c2a25efafaef28d19c3a4faa8eb7fce751aa"
    },
    {
      "model_id": "bigcode/astraios-adapterp",
      "scanned_at": "2026-07-15T02:00:35.110052Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "ffd330bf96c0901f143f81876c6896e4be4da91109c9398d77bcbe6244395eda"
    },
    {
      "model_id": "bigcode/astraios-fft",
      "scanned_at": "2026-07-15T02:00:37.856595Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "checkpoints-fft/checkpoint-200",
          "confidence": 0.9,
          "raw_context": "_name_or_path: checkpoints-fft/checkpoint-200"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "701e7891a3beec2f73f8da04a3965ffc970a3910011390678e89388057fab475"
    },
    {
      "model_id": "bigcode/astraios-ia3",
      "scanned_at": "2026-07-15T02:00:40.628349Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "fc5212e8849cc02fb2c2e9ee546db1c427fccd5693f812b2ecf8046845699cf7"
    },
    {
      "model_id": "bigcode/astraios-lora",
      "scanned_at": "2026-07-15T02:00:43.379391Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "1bf4e7d62b8a715c27a2e8cbff890d90c304f6d893403459f0153998cc609bb1"
    },
    {
      "model_id": "bigcode/astraios-parallel",
      "scanned_at": "2026-07-15T02:00:46.172792Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "e21af2f72c844b007038532264a605aa180d195d75aa57255456e1c5cfd77779"
    },
    {
      "model_id": "bigcode/astraios-ptuning",
      "scanned_at": "2026-07-15T02:00:48.927983Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/guanaco-commits",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/guanaco-commits"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoderBase on CommitPackFT & OASST as described in the A"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "td><a href=https://huggingface.co/datasets/code_x_glue_cc_clone_detection_big_clone_bench>BigCloneBench<"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/guanaco-commits"
      ],
      "inferred_datasets": [
        "glue",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "f4d3666f21293ad792934c1659927017e28ef8f64edf6148aa0f40a26ac10b14"
    },
    {
      "model_id": "bigcode/bcb_update",
      "scanned_at": "2026-07-15T02:00:51.682362Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "0241f50083d7f30be413be3d0810de22f193304bf2d94f251c47a9b3a0ad3104"
    },
    {
      "model_id": "bigcode/deepseekcoder-33b-codeqwen-align-subset",
      "scanned_at": "2026-07-15T02:00:54.492967Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).  - **Hardware Type:** [More"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.35,
      "provenance_hash": "b7f29ee6d78b8c2b1488328da97c73ae9a52d08e30f949680b3e6bc86da385bc"
    },
    {
      "model_id": "bigcode/gpt_bigcode-santacoder",
      "scanned_at": "2026-07-15T02:00:57.249754Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "banner",
          "confidence": 0.6,
          "raw_context": ": 18.13       verified: false ---  # SantaCoder  ![banner](https://huggingface.co/datasets/bigcode/admin/resolve/main/banner.png)  Play with"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "github code",
          "confidence": 0.7,
          "raw_context": "# Use  ## Intended use  The model was trained on GitHub code. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": ": text-generation     dataset:       type: code_x_glue_ct_code_to_text       name: CodeXGLUE code-to-tex"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack"
      ],
      "inferred_datasets": [
        "glue",
        "github code"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "openrail",
      "provenance_score": 0.6,
      "provenance_hash": "f298ca6e7b28bf015d0ef66f774f25efb0178af0825720ae68e49182960f8843"
    },
    {
      "model_id": "bigcode/octocoder",
      "scanned_at": "2026-07-15T02:01:00.013764Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/commitpackft",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/commitpackft"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/oasst-octopack",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/oasst-octopack"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoder on CommitPackFT & OASST as described in the OctoP"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "model with 15.5B parameters created by finetuning StarCoder on CommitPackFT & OASST as described in the OctoP"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "uction Tuning Code Large Language Models](https://arxiv.org/abs/2308.07124) - **Languages:** 80+ Programm"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/oasst-octopack",
        "bigcode/commitpackft"
      ],
      "inferred_datasets": [
        "arxiv",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.7,
      "provenance_hash": "8caaa041c21d79de6683ac6e0741e06aecd9751dc2874402226b3cdf5fc90c8c"
    },
    {
      "model_id": "bigcode/octogeex",
      "scanned_at": "2026-07-15T02:01:02.763281Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/commitpackft",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/commitpackft"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/oasst-octopack",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/oasst-octopack"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "CommitPackFT",
          "confidence": 0.6,
          "raw_context": "X2](https://huggingface.co/THUDM/codegeex2-6b) on [CommitPackFT](https://huggingface.co/datasets/bigcode/commitpackft) & [OASST](https://huggingfac"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "OASST",
          "confidence": 0.6,
          "raw_context": "//huggingface.co/datasets/bigcode/commitpackft) & [OASST](https://huggingface.co/datasets/bigcode/oasst-octopack) as described in the OctoPa"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "gface.co/bigcode/octocoder>OctoCoder</a></th> <td>StarCoder (16B parameters) instruction tuned on CommitPackF"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "gface.co/bigcode/octocoder>OctoCoder</a></th> <td>StarCoder (16B parameters) instruction tuned on CommitPackF"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "uction Tuning Code Large Language Models](https://arxiv.org/abs/2308.07124) - **Languages:** 100+ Program"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "THUDM/codegeex2-6b",
          "confidence": 0.9,
          "raw_context": "_name_or_path: THUDM/codegeex2-6b"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "chatglm",
          "confidence": 0.5,
          "raw_context": "model_type: chatglm"
        }
      ],
      "declared_datasets": [
        "bigcode/oasst-octopack",
        "bigcode/commitpackft"
      ],
      "inferred_datasets": [
        "arxiv",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.6,
      "provenance_hash": "be69cf90fd6bb796d2ffcf640930e57d116b60dc40aacdf1b72e30a46a48c4d6"
    },
    {
      "model_id": "bigcode/report",
      "scanned_at": "2026-07-15T02:01:05.715567Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.1,
      "provenance_hash": "4416642ff97cc010af683bafbdb46f5797ddec6b670fda07906d478a072170fc"
    },
    {
      "model_id": "bigcode/santacoder",
      "scanned_at": "2026-07-15T02:01:08.464189Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "banner",
          "confidence": 0.6,
          "raw_context": ": 18.13       verified: false ---  # SantaCoder  ![banner](https://huggingface.co/datasets/bigcode/admin/resolve/main/banner.png)  Play with"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Stack",
          "confidence": 0.6,
          "raw_context": "ed on the Python, Java, and JavaScript subset of [The Stack (v1.1)](https://huggingface.co/datasets/bigcode/t"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "`<fim_prefix>, <fim_suffix>, <fim_middle>` as in StarCoder models.  ### Load other checkpoints We upload the"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "github code",
          "confidence": 0.7,
          "raw_context": "# Use  ## Intended use  The model was trained on GitHub code. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "`<fim_prefix>, <fim_suffix>, <fim_middle>` as in StarCoder models.  ### Load other checkpoints We upload the"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": ": text-generation     dataset:       type: code_x_glue_ct_code_to_text       name: CodeXGLUE code-to-tex"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "e main model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150), a context window of 2048 tok"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the stack",
          "confidence": 0.7,
          "raw_context": "ed on the Python, Java, and JavaScript subset of [The Stack (v1.1)](https://huggingface.co/datasets/bigcode/t"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack"
      ],
      "inferred_datasets": [
        "glue",
        "github code",
        "the stack",
        "arxiv",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.7,
      "provenance_hash": "4c3ff9276f6bd4b990ae04a7f52ad8c8a2a94bbd7258626d25cc08066b6eb753"
    },
    {
      "model_id": "bigcode/santacoder-cf",
      "scanned_at": "2026-07-15T02:01:11.264091Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.1,
      "provenance_hash": "d5c429d0a6c52af5028c891b86202a664a4d87105837468eb92ab997d5f01efa"
    },
    {
      "model_id": "bigcode/santacoder-fast-inference",
      "scanned_at": "2026-07-15T02:01:14.121628Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "openrail",
      "provenance_score": 0.1,
      "provenance_hash": "10244153404b1bd8b59e6cd4d49cb3d9e6bfddbf03bcac30891ea0ad7134b8df"
    },
    {
      "model_id": "bigcode/santacoder-ldf",
      "scanned_at": "2026-07-15T02:01:16.873315Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Line Diff Format introduced in [OctoPack](https://arxiv.org/abs/2308.07124)."
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "9f8e0cbb9e102657536e3f71ffd434fe95d00dd581171812531d108fc15b2bb6"
    },
    {
      "model_id": "bigcode/santacoder-megatron",
      "scanned_at": "2026-07-15T02:01:19.728080Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "banner",
          "confidence": 0.6,
          "raw_context": ": 18.13       verified: false ---  # SantaCoder  ![banner](https://huggingface.co/datasets/bigcode/admin/resolve/main/banner.png)  Play with"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "github code",
          "confidence": 0.7,
          "raw_context": "# Use  ## Intended use  The model was trained on GitHub code. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": ": text-generation     dataset:       type: code_x_glue_ct_code_to_text       name: CodeXGLUE code-to-tex"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack"
      ],
      "inferred_datasets": [
        "glue",
        "github code"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "openrail",
      "provenance_score": 0.6,
      "provenance_hash": "721b6b046d291892c7410f63b5c5a0325170905ca9b875e32017cc1e82b16e87"
    },
    {
      "model_id": "bigcode/santacoderpack",
      "scanned_at": "2026-07-15T02:01:22.559245Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/commitpack-subset-cf",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/commitpack-subset-cf"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "uction Tuning Code Large Language Models](https://arxiv.org/abs/2308.07124) - **Languages:** Python, Java"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [
        "bigcode/commitpack-subset-cf"
      ],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.55,
      "provenance_hash": "988367f628d335092f61474ee0df819130ac1ad6937572e3b8be753524498244"
    },
    {
      "model_id": "bigcode/starcoder-co-format",
      "scanned_at": "2026-07-15T02:01:25.339034Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "bigcode/starcoder",
          "confidence": 0.9,
          "raw_context": "_name_or_path: bigcode/starcoder"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "fad93c899d5841643c89f2217157a9ba37276d7d5e859ab7bc908095d6fa9c28"
    },
    {
      "model_id": "bigcode/starcoder-co-manual",
      "scanned_at": "2026-07-15T02:01:28.091371Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "bigcode/starcoder",
          "confidence": 0.9,
          "raw_context": "_name_or_path: bigcode/starcoder"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "2b236b97a2e24d013ca80a7832d36e9dd0957c6a4c5a7bb85126b4c9b2b4aed6"
    },
    {
      "model_id": "bigcode/starcoder-co-target",
      "scanned_at": "2026-07-15T02:01:30.923443Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "bigcode/starcoder",
          "confidence": 0.9,
          "raw_context": "_name_or_path: bigcode/starcoder"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "c64bdb6857b8ba26ed83af2730f48416aa694a7a5069e82cb84ff1093ee9380d"
    },
    {
      "model_id": "bigcode/starcoder-cxo",
      "scanned_at": "2026-07-15T02:01:33.667836Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "bigcode/starcoder",
          "confidence": 0.9,
          "raw_context": "_name_or_path: bigcode/starcoder"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "a76cf8e647ed90f1eb3cd79c69ae6d142d361fa602d9871b06ddbc04b29a44c4"
    },
    {
      "model_id": "bigcode/starcoder-cxso",
      "scanned_at": "2026-07-15T02:01:36.421989Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "bigcode/starcoder",
          "confidence": 0.9,
          "raw_context": "_name_or_path: bigcode/starcoder"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "f44e708cdf8374704bcaaecbc1d267f29e8342ad49c7cc1c94acd5ca0382c93e"
    },
    {
      "model_id": "bigcode/starcoder-megatron",
      "scanned_at": "2026-07-15T02:01:39.385721Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-dedup",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-dedup"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-dedup"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.2,
      "provenance_hash": "b3ff582897e05ed7f3f5bf94acb798ef6bdeaa3534f1da30b1500727955564c5"
    },
    {
      "model_id": "bigcode/starcoder-o",
      "scanned_at": "2026-07-15T02:01:42.128251Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "6b34077b33ce9b9475ffa0ed95bb18bf592faa1490ba4e75ef7ad1540861198f"
    },
    {
      "model_id": "bigcode/starcoder-xo",
      "scanned_at": "2026-07-15T02:01:44.882347Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "bigcode/starcoder",
          "confidence": 0.9,
          "raw_context": "_name_or_path: bigcode/starcoder"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "9c732000a6b1a8cdd1431fd5913ffbba815409d170245e5fcdc832ab981a0b48"
    },
    {
      "model_id": "bigcode/starcoder2-15b",
      "scanned_at": "2026-07-15T02:01:47.627742Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-v2-train",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-v2-train"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "GitHub code as well as additional selected",
          "confidence": 0.6,
          "raw_context": "anguages  ## Use  ### Intended use  The model was trained on GitHub code as well as additional selected data sources such as Arxiv and Wikipedia. As such it i"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.6,
          "raw_context": "e: transformers tags: - code model-index: - name: starcoder2-15b   results:   - task:       type: text-genera"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Stack",
          "confidence": 0.6,
          "raw_context": "model trained on 600+ programming languages from [The Stack v2](https://huggingface.co/datasets/bigcode/the-s"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "Wikipedia",
          "confidence": 0.6,
          "raw_context": "dditional selected data sources such as Arxiv and Wikipedia. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "github code",
          "confidence": 0.7,
          "raw_context": "# Use  ### Intended use  The model was trained on GitHub code as well as additional selected data sources such"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "e: transformers tags: - code model-index: - name: starcoder2-15b   results:   - task:       type: text-genera"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "The model uses [Grouped Query Attention](https://arxiv.org/abs/2305.13245), [a context window of 16,384"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.7,
          "raw_context": "dditional selected data sources such as Arxiv and Wikipedia. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the stack",
          "confidence": 0.7,
          "raw_context": "model trained on 600+ programming languages from [The Stack v2](https://huggingface.co/datasets/bigcode/the-s"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/aot/checkpoints/15b/config.json",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /aot/checkpoints/15b/config.json"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "starcoder2",
          "confidence": 0.5,
          "raw_context": "model_type: starcoder2"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-v2-train"
      ],
      "inferred_datasets": [
        "wikipedia",
        "github code",
        "the stack",
        "arxiv",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.7,
      "provenance_hash": "448e8cf690830a2c1ad997613c9ed55f93526d41023fbdac985d505eaadf2230"
    },
    {
      "model_id": "bigcode/starcoder2-15b-instruct-v0.1",
      "scanned_at": "2026-07-15T02:01:50.373104Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/self-oss-instruct-sc2-exec-filter-50k",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/self-oss-instruct-sc2-exec-filter-50k"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "bigcode/starcoder2-15b",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:bigcode/starcoder2-15b"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:bigcode/starcoder2-15b",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:bigcode/starcoder2-15b"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "Banner",
          "confidence": 0.6,
          "raw_context": "d Permissive Self-Alignment for Code Generation  ![Banner](https://huggingface.co/datasets/bigcode/starcoder2-instruct-assets/resolve/main/ba"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigcode/self-oss-instruct-sc2-exec-filter-50k",
          "confidence": 0.8,
          "raw_context": "ode-project/starcoder2-self-align) - **Dataset:** [bigcode/self-oss-instruct-sc2-exec-filter-50k](https://huggingface.co/datasets/bigcode/self-oss-instruct-sc2-exec-filter-50k/) -"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "EvalPlus",
          "confidence": 0.6,
          "raw_context": "luation on EvalPlus, LiveCodeBench, and DS-1000  ![EvalPlus](https://huggingface.co/datasets/bigcode/starcoder2-instruct-assets/resolve/main/ev"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.6,
          "raw_context": "pipeline_tag: text-generation base_model: bigcode/starcoder2-15b datasets: - bigcode/self-oss-instruct-sc2-ex"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Stack",
          "confidence": 0.6,
          "raw_context": "pipeline: 1. Original seed dataset filtered from The Stack v1: https://huggingface.co/datasets/bigcode/pytho"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "bigcode/starcoder2-15b",
          "confidence": 0.85,
          "raw_context": "--- pipeline_tag: text-generation base_model: bigcode/starcoder2-15b datasets: - bigcode/self-oss-instruct-sc2-exec-fi"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "pipeline_tag: text-generation base_model: bigcode/starcoder2-15b datasets: - bigcode/self-oss-instruct-sc2-ex"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ha and Lingming Zhang},   year={2024},   journal={arXiv preprint arXiv:2410.24198} } ```  ## Use  ### Int"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the stack",
          "confidence": 0.7,
          "raw_context": "pipeline: 1. Original seed dataset filtered from The Stack v1: https://huggingface.co/datasets/bigcode/pytho"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "starcoder2",
          "confidence": 0.5,
          "raw_context": "model_type: starcoder2"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:bigcode/starcoder2-15b",
          "value": "GitHub code as well as additional selected",
          "confidence": 0.48,
          "raw_context": "anguages  ## Use  ### Intended use  The model was trained on GitHub code as well as additional selected data sources such as Arxiv and Wikipedia. As such it i"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:bigcode/starcoder2-15b",
          "value": "starcoder",
          "confidence": 0.48,
          "raw_context": "e: transformers tags: - code model-index: - name: starcoder2-15b   results:   - task:       type: text-genera"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:bigcode/starcoder2-15b",
          "value": "The Stack",
          "confidence": 0.48,
          "raw_context": "model trained on 600+ programming languages from [The Stack v2](https://huggingface.co/datasets/bigcode/the-s"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:bigcode/starcoder2-15b",
          "value": "Wikipedia",
          "confidence": 0.48,
          "raw_context": "dditional selected data sources such as Arxiv and Wikipedia. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:bigcode/starcoder2-15b",
          "value": "github code",
          "confidence": 0.5599999999999999,
          "raw_context": "# Use  ### Intended use  The model was trained on GitHub code as well as additional selected data sources such"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:bigcode/starcoder2-15b",
          "value": "starcoder",
          "confidence": 0.5599999999999999,
          "raw_context": "e: transformers tags: - code model-index: - name: starcoder2-15b   results:   - task:       type: text-genera"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:bigcode/starcoder2-15b",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "The model uses [Grouped Query Attention](https://arxiv.org/abs/2305.13245), [a context window of 16,384"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:bigcode/starcoder2-15b",
          "value": "wikipedia",
          "confidence": 0.5599999999999999,
          "raw_context": "dditional selected data sources such as Arxiv and Wikipedia. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:bigcode/starcoder2-15b",
          "value": "the stack",
          "confidence": 0.5599999999999999,
          "raw_context": "model trained on 600+ programming languages from [The Stack v2](https://huggingface.co/datasets/bigcode/the-s"
        }
      ],
      "declared_datasets": [
        "bigcode/self-oss-instruct-sc2-exec-filter-50k"
      ],
      "inferred_datasets": [
        "github code",
        "the stack",
        "GitHub code as well as additional selected",
        "wikipedia",
        "The Stack",
        "arxiv",
        "Wikipedia",
        "starcoder"
      ],
      "base_model": "bigcode/starcoder2-15b",
      "base_model_chain": [
        "bigcode/starcoder2-15b"
      ],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.8,
      "provenance_hash": "729c37600b8429a5bd8734fcc3be4fd1f123a4a45b655fe5b7ecbb2547ad203b"
    },
    {
      "model_id": "bigcode/starcoder2-7b",
      "scanned_at": "2026-07-15T02:01:53.128465Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-v2-train",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-v2-train"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "GitHub code as well as additional selected",
          "confidence": 0.6,
          "raw_context": "anguages  ## Use  ### Intended use  The model was trained on GitHub code as well as additional selected data sources such as Arxiv and Wikipedia. As such it i"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.6,
          "raw_context": "e: transformers tags: - code model-index: - name: starcoder2-7b   results:   - task:       type: text-generat"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Stack",
          "confidence": 0.6,
          "raw_context": "r model trained on 17 programming languages from [The Stack v2](https://huggingface.co/datasets/bigcode/the-s"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "Wikipedia",
          "confidence": 0.6,
          "raw_context": "dditional selected data sources such as Arxiv and Wikipedia. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "github code",
          "confidence": 0.7,
          "raw_context": "# Use  ### Intended use  The model was trained on GitHub code as well as additional selected data sources such"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "e: transformers tags: - code model-index: - name: starcoder2-7b   results:   - task:       type: text-generat"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "The model uses [Grouped Query Attention](https://arxiv.org/abs/2305.13245), [a context window of 16,384"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.7,
          "raw_context": "dditional selected data sources such as Arxiv and Wikipedia. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the stack",
          "confidence": 0.7,
          "raw_context": "r model trained on 17 programming languages from [The Stack v2](https://huggingface.co/datasets/bigcode/the-s"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "starcoder2",
          "confidence": 0.5,
          "raw_context": "model_type: starcoder2"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-v2-train"
      ],
      "inferred_datasets": [
        "wikipedia",
        "github code",
        "the stack",
        "arxiv",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.7,
      "provenance_hash": "2078de98471b5309f21ce827dd8a61217b18c05b44c1c9600b99e308e30c0f06"
    },
    {
      "model_id": "bigcode/starcoder2-tokenizer",
      "scanned_at": "2026-07-15T02:01:55.872032Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "ab5e0be4ccffd02ecaea082d117ef2a7b44d46d27578ee149b34b8728da8c440"
    },
    {
      "model_id": "bigcode/starcoderbase",
      "scanned_at": "2026-07-15T02:01:58.622494Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-dedup",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-dedup"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-dedup"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.2,
      "provenance_hash": "d60f05d762a47543938a670510575d3abbe1b1b690f74187a12def449f070269"
    },
    {
      "model_id": "bigcode/starcoderbase-1b",
      "scanned_at": "2026-07-15T02:02:01.359104Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-dedup",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-dedup"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-dedup"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.2,
      "provenance_hash": "770b1702ff1ae1784913d596a59a92b395cd69e855db098e1ac3c14f8a47047a"
    },
    {
      "model_id": "bigcode/starcoderbase-3b",
      "scanned_at": "2026-07-15T02:02:04.087261Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-dedup",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-dedup"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-dedup"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.2,
      "provenance_hash": "4684098ebf8b6fb04d2c5126175f7db26acc05bde8b20cb3be31931468670500"
    },
    {
      "model_id": "bigcode/starcoderbase-7b",
      "scanned_at": "2026-07-15T02:02:07.382702Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-dedup",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-dedup"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-dedup"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.2,
      "provenance_hash": "de645149359ad1d6a2012c30cdde214b26d3303c0aef57a70122add8ea064462"
    },
    {
      "model_id": "bigcode/starcoderbase-megatron",
      "scanned_at": "2026-07-15T02:02:10.111512Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-dedup",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-dedup"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-dedup"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.2,
      "provenance_hash": "5732c36b6bf69056979b132ad83c28ac8d8670c86b31eacf10090cdd42601eb4"
    },
    {
      "model_id": "bigcode/starcoderplus",
      "scanned_at": "2026-07-15T02:02:12.849537Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-dedup",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-dedup"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "tiiuae/falcon-refinedweb",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:tiiuae/falcon-refinedweb"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-dedup",
        "tiiuae/falcon-refinedweb"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.2,
      "provenance_hash": "cd5281f1b801daaeccd80beeac9ddf8c2a182a7551b9b830f8eacce867a43b03"
    },
    {
      "model_id": "bigcode/starcoderplus-megatron",
      "scanned_at": "2026-07-15T02:02:15.577781Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-dedup",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-dedup"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "tiiuae/falcon-refinedweb",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:tiiuae/falcon-refinedweb"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "RedefinedWeb",
          "confidence": 0.6,
          "raw_context": "base) on 600B tokens from the English web dataset [RedefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)  combined with [StarCode"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoderData",
          "confidence": 0.6,
          "raw_context": "datasets/tiiuae/falcon-refinedweb)  combined with [StarCoderData](https://huggingface.co/datasets/bigcode/starcoderdata) from [The Stack (v1.2)](htt"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "e: transformers tags: - code model-index: - name: StarCoderPlus   results:   - task:       type: text-generat"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Stack",
          "confidence": 0.6,
          "raw_context": "gingface.co/datasets/bigcode/starcoderdata) from [The Stack (v1.2)](https://huggingface.co/datasets/bigcode/t"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "Wikipedia",
          "confidence": 0.6,
          "raw_context": "/huggingface.co/datasets/bigcode/the-stack) and a Wikipedia dataset. It's a 15.5B parameter Language Model tr"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "github code",
          "confidence": 0.7,
          "raw_context": "ntended use  The model was trained on English and GitHub code. As such it is _not_ an instruction model and com"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "refinedweb",
          "confidence": 0.7,
          "raw_context": "tasets: - bigcode/the-stack-dedup - tiiuae/falcon-refinedweb metrics: - code_eval - mmlu - arc - hellaswag - t"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "e: transformers tags: - code model-index: - name: StarCoderPlus   results:   - task:       type: text-generat"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "s. The model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150), [a context window of 8192 to"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.7,
          "raw_context": "/huggingface.co/datasets/bigcode/the-stack) and a Wikipedia dataset. It's a 15.5B parameter Language Model tr"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the stack",
          "confidence": 0.7,
          "raw_context": "gingface.co/datasets/bigcode/starcoderdata) from [The Stack (v1.2)](https://huggingface.co/datasets/bigcode/t"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-dedup",
        "tiiuae/falcon-refinedweb"
      ],
      "inferred_datasets": [
        "wikipedia",
        "github code",
        "refinedweb",
        "the stack",
        "arxiv",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.7,
      "provenance_hash": "082b5d4ae4df2448f46e7f35054d6e1c6822c435a8b9e54d43dc384fde259f29"
    },
    {
      "model_id": "bigcode/starencoder",
      "scanned_at": "2026-07-15T02:02:18.327539Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b9f349e752647acc91479a11b47f86c0cd7466ef76ec1b22132c9f3d600543e4"
    },
    {
      "model_id": "bigcode/starpii",
      "scanned_at": "2026-07-15T02:02:21.087076Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/pii-annotated-toloka-donwsample-emails",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/pii-annotated-toloka-donwsample-emails"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/pseudo-labeled-python-data-pii-detection-filtered",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/pseudo-labeled-python-data-pii-detection-filtered"
        }
      ],
      "declared_datasets": [
        "bigcode/pii-annotated-toloka-donwsample-emails",
        "bigcode/pseudo-labeled-python-data-pii-detection-filtered"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.2,
      "provenance_hash": "a6f5f2c90bfafa82665512d8ba1558e32d19d16df4231b88bc9499230a256585"
    },
    {
      "model_id": "bigcode/tiny_starcoder_py",
      "scanned_at": "2026-07-15T02:02:23.860927Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigcode/the-stack-dedup",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigcode/the-stack-dedup"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoderData",
          "confidence": 0.6,
          "raw_context": "QA & FIM). It was trained on the Python data from [StarCoderData](https://huggingface.co/datasets/bigcode/starcoderdata) for ~6 epochs which amounts"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "Python",
          "confidence": 0.6,
          "raw_context": "starcoder) (8k context length, MQA & FIM). It was trained on the Python data from [StarCoderData](https://huggingface.co/datas"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "StarCoder",
          "confidence": 0.6,
          "raw_context": "ansformers tags: - code model-index: - name: Tiny-StarCoder-Py   results:   - task:       type: text-generati"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "github code",
          "confidence": 0.7,
          "raw_context": "# Use  ### Intended use  The model was trained on GitHub code, to assist with some tasks like [Assisted Generat"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "starcoder",
          "confidence": 0.7,
          "raw_context": "ansformers tags: - code model-index: - name: Tiny-StarCoder-Py   results:   - task:       type: text-generati"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/fsx/bigcode/tinystarcoder/saves/large-model",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /fsx/bigcode/tinystarcoder/saves/large-model"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt_bigcode",
          "confidence": 0.5,
          "raw_context": "model_type: gpt_bigcode"
        }
      ],
      "declared_datasets": [
        "bigcode/the-stack-dedup"
      ],
      "inferred_datasets": [
        "github code",
        "starcoder"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigcode-openrail-m",
      "provenance_score": 0.6,
      "provenance_hash": "52722382655e5c31af04913256767ca42b42931cb0b1e2e5e84e57d950575c92"
    },
    {
      "model_id": "bigcode/tokenizer-ablations",
      "scanned_at": "2026-07-15T02:02:26.597124Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "96bce468e74e6311db34e57625dd64af8d4163afba908fc310b059b6428827ea"
    },
    {
      "model_id": "bigcode/tokenizer-the-stack-march-sample",
      "scanned_at": "2026-07-15T02:02:29.359532Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "06ce3d35592f3a62d9bd4206a8fe8b8a18b881c9c71fea379c4b2b5fade2654c"
    },
    {
      "model_id": "bigcode/tokenizer-the-stack-march-sample-v2",
      "scanned_at": "2026-07-15T02:02:32.121855Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "8438757f11f9b9179a62ea001d5c7961e19218be7cf11f0cab556001db9433c2"
    },
    {
      "model_id": "bigcode/tokenizer-the-stack-march-sample-v3",
      "scanned_at": "2026-07-15T02:02:34.939399Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "0f164a2e02a188a8b5cdbe340ea3cc47e806ebe17a28ccf9cdd634530d01c2ad"
    },
    {
      "model_id": "bigcode/tokenizer-the-stack-march-sample-v3-no-prefix-spaces",
      "scanned_at": "2026-07-15T02:02:37.744528Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "d05ce098a7bc3bbe4300f73a0219851f5a1f5e1bc5ea8a2457e923f4968b62de"
    },
    {
      "model_id": "bigscience/T0",
      "scanned_at": "2026-07-15T02:02:40.542018Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/P3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/P3"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "squad",
          "confidence": 0.7,
          "raw_context": "ook QA, PiQA, RACE, HellaSwag<br>- Extractive QA: SQuAD v2<br>- Closed-Book QA: Trivia QA, Web Questions|"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "th a masked language modeling-style objective on [C4](https://huggingface.co/datasets/c4). We use the"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "e as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "p|Same as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "lable the models presented in our [paper](https://arxiv.org/abs/2110.08207) along with the ablation model"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "t5",
          "confidence": 0.5,
          "raw_context": "model_type: t5"
        }
      ],
      "declared_datasets": [
        "bigscience/P3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "squad",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.7,
      "provenance_hash": "8e84b372f3616a3aa1108e8fbe0f3dd441421db0e3e57daedfa6615924069fba"
    },
    {
      "model_id": "bigscience/T0_3B",
      "scanned_at": "2026-07-15T02:02:43.337915Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/P3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/P3"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "squad",
          "confidence": 0.7,
          "raw_context": "ook QA, PiQA, RACE, HellaSwag<br>- Extractive QA: SQuAD v2<br>- Closed-Book QA: Trivia QA, Web Questions|"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "th a masked language modeling-style objective on [C4](https://huggingface.co/datasets/c4). We use the"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "e as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "p|Same as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "lable the models presented in our [paper](https://arxiv.org/abs/2110.08207) along with the ablation model"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "t5",
          "confidence": 0.5,
          "raw_context": "model_type: t5"
        }
      ],
      "declared_datasets": [
        "bigscience/P3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "squad",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.7,
      "provenance_hash": "0fa466674fce54e971f448d7a86e69cfa27505d68791f5fd64e31ccca2d55497"
    },
    {
      "model_id": "bigscience/T0_original_task_only",
      "scanned_at": "2026-07-15T02:02:46.099248Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/P3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/P3"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "squad",
          "confidence": 0.7,
          "raw_context": "ook QA, PiQA, RACE, HellaSwag<br>- Extractive QA: SQuAD v2<br>- Closed-Book QA: Trivia QA, Web Questions|"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "th a masked language modeling-style objective on [C4](https://huggingface.co/datasets/c4). We use the"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "e as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "p|Same as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "lable the models presented in our [paper](https://arxiv.org/abs/2110.08207) along with the ablation model"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "t5",
          "confidence": 0.5,
          "raw_context": "model_type: t5"
        }
      ],
      "declared_datasets": [
        "bigscience/P3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "squad",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.7,
      "provenance_hash": "35c4a1528da8ad207a7e90a1d1e6048b737edab7c3aafa1deef7e0d508caa742"
    },
    {
      "model_id": "bigscience/T0_single_prompt",
      "scanned_at": "2026-07-15T02:02:48.887533Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/P3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/P3"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "squad",
          "confidence": 0.7,
          "raw_context": "ook QA, PiQA, RACE, HellaSwag<br>- Extractive QA: SQuAD v2<br>- Closed-Book QA: Trivia QA, Web Questions|"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "th a masked language modeling-style objective on [C4](https://huggingface.co/datasets/c4). We use the"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "e as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "p|Same as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "lable the models presented in our [paper](https://arxiv.org/abs/2110.08207) along with the ablation model"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "t5",
          "confidence": 0.5,
          "raw_context": "model_type: t5"
        }
      ],
      "declared_datasets": [
        "bigscience/P3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "squad",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.7,
      "provenance_hash": "064d922ec58dd488b3dface121918099db0d30d9cb6cf1158536792425a46fd9"
    },
    {
      "model_id": "bigscience/T0p",
      "scanned_at": "2026-07-15T02:02:51.638898Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/P3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/P3"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "squad",
          "confidence": 0.7,
          "raw_context": "ook QA, PiQA, RACE, HellaSwag<br>- Extractive QA: SQuAD v2<br>- Closed-Book QA: Trivia QA, Web Questions|"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "th a masked language modeling-style objective on [C4](https://huggingface.co/datasets/c4). We use the"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "e as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "p|Same as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "lable the models presented in our [paper](https://arxiv.org/abs/2110.08207) along with the ablation model"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "t5",
          "confidence": 0.5,
          "raw_context": "model_type: t5"
        }
      ],
      "declared_datasets": [
        "bigscience/P3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "squad",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.7,
      "provenance_hash": "f7fc35a2e02d9009c92843a312d42c759709910523662cafdef2007b124124dc"
    },
    {
      "model_id": "bigscience/T0pp",
      "scanned_at": "2026-07-15T02:02:54.407284Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/P3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/P3"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "squad",
          "confidence": 0.7,
          "raw_context": "ook QA, PiQA, RACE, HellaSwag<br>- Extractive QA: SQuAD v2<br>- Closed-Book QA: Trivia QA, Web Questions|"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "th a masked language modeling-style objective on [C4](https://huggingface.co/datasets/c4). We use the"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "e as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "p|Same as T0p with a few additional datasets from SuperGLUE (excluding NLI sets):<br>- BoolQ<br>- COPA<br>- M"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "lable the models presented in our [paper](https://arxiv.org/abs/2110.08207) along with the ablation model"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "t5",
          "confidence": 0.5,
          "raw_context": "model_type: t5"
        }
      ],
      "declared_datasets": [
        "bigscience/P3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "squad",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.7,
      "provenance_hash": "fa49d24c750d81d4f78cd909ee82cd221a92c76b007814c7b4596a37777db1e0"
    },
    {
      "model_id": "bigscience/bigscience-small-testing",
      "scanned_at": "2026-07-15T02:02:57.166691Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/home/younes/Desktop/Work/data/megatron-debug/",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /home/younes/Desktop/Work/data/megatron-debug/"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "1c55a4b53666ce46b9f185b89ceee0dff8f2d008b515c51295010811a9a94309"
    },
    {
      "model_id": "bigscience/bloom-1b1",
      "scanned_at": "2026-07-15T02:02:59.925049Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "c77a4f6173d56bc1eb4f884d87d5082810d516c4633a417bd699c2e3ab467547"
    },
    {
      "model_id": "bigscience/bloom-1b1-intermediate",
      "scanned_at": "2026-07-15T02:03:02.808965Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "vast amounts of text",
          "confidence": 0.6,
          "raw_context": "a Large Language Model (LLM), meaning that it is trained on vast amounts of text data using industrial-scale computational resources."
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "5ef8fc3e302e828621bdf3c767bbb534712bdaabeca5e3248029a87606c35378"
    },
    {
      "model_id": "bigscience/bloom-1b7",
      "scanned_at": "2026-07-15T02:03:05.614820Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "ers  -   Non-commercial entities  -   Community advocates, including human and civil rights groups  ###"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "7e5b10b3cfca3144de41a0345df38f87bfa9bf5df6bf8db70a7e62dd502a03c0"
    },
    {
      "model_id": "bigscience/bloom-1b7-intermediate",
      "scanned_at": "2026-07-15T02:03:08.486004Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "vast amounts of text",
          "confidence": 0.6,
          "raw_context": "a Large Language Model (LLM), meaning that it is trained on vast amounts of text data using industrial-scale computational resources."
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "25c4aaf63d7e03e70874a0aac4ebd06196c897d86a769750fb3bd8a96ecab5eb"
    },
    {
      "model_id": "bigscience/bloom-3b",
      "scanned_at": "2026-07-15T02:03:11.262859Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "pubmed",
          "confidence": 0.7,
          "raw_context": "name: text generation     dataset:       name: pubmedqa       type: pubmedqa     metrics:     - name: a"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "pubmed",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.55,
      "provenance_hash": "cc5a5e483cdbfcf1c3031d7e1c09d1016f66ec46f6ec27d6e25002cc34969d11"
    },
    {
      "model_id": "bigscience/bloom-3b-intermediate",
      "scanned_at": "2026-07-15T02:03:14.069601Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "vast amounts of text",
          "confidence": 0.6,
          "raw_context": "a Large Language Model (LLM), meaning that it is trained on vast amounts of text data using industrial-scale computational resources."
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "e5e479f3f0dbcc7cb64d2ef0a33ef29cba8abf02fb7d265755d9c9429655c47a"
    },
    {
      "model_id": "bigscience/bloom-560m-intermediate",
      "scanned_at": "2026-07-15T02:03:16.965894Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "vast amounts of text",
          "confidence": 0.6,
          "raw_context": "a Large Language Model (LLM), meaning that it is trained on vast amounts of text data using industrial-scale computational resources."
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "73eabf7c08f9f75f4662cdc69ac4e2492017b9ad59e3b94193344990f40a7e62"
    },
    {
      "model_id": "bigscience/bloom-7b1",
      "scanned_at": "2026-07-15T02:03:19.761099Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "67db3a5d0adc779ec1ee45f49403dc2c2b42830ee5757f4364e1a88d9fd0c0f6"
    },
    {
      "model_id": "bigscience/bloom-7b1-intermediate",
      "scanned_at": "2026-07-15T02:03:22.928453Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "vast amounts of text",
          "confidence": 0.6,
          "raw_context": "a Large Language Model (LLM), meaning that it is trained on vast amounts of text data using industrial-scale computational resources."
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "82facb562462c4d812ba4defdbcec2b41837c61e1e8feac554eda097df5cc112"
    },
    {
      "model_id": "bigscience/bloom-7b1-petals",
      "scanned_at": "2026-07-15T02:03:25.719580Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "27770f7401bae90b4b13134561efbe05ec9d11fe82585c57f3376e228d631ec3"
    },
    {
      "model_id": "bigscience/bloom-intermediate",
      "scanned_at": "2026-07-15T02:03:28.533070Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "vast amounts of text",
          "confidence": 0.6,
          "raw_context": "a Large Language Model (LLM), meaning that it is trained on vast amounts of text data using industrial-scale computational resources."
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "118ec0b34250d1e87a09aeaa690cda106cd6e10f2c9ecc36528d722eb45c2fda"
    },
    {
      "model_id": "bigscience/bloom-petals",
      "scanned_at": "2026-07-15T02:03:31.311867Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "bd5a7123139194f8cba56a3f4bef1dc604130db47f27a84fadeb50eefe30d2df"
    },
    {
      "model_id": "bigscience/bloomz",
      "scanned_at": "2026-07-15T02:03:34.072119Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "uggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "split: validation       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094     metrics:     - type: Ac"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "arxiv",
        "superglue"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.8,
      "provenance_hash": "8309db46a47e152089626005daf8bb45b159913cda1bb9051f6b62f453ee64b4"
    },
    {
      "model_id": "bigscience/bloomz-1b1",
      "scanned_at": "2026-07-15T02:03:36.849543Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "uggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "split: validation       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094     metrics:     - type: Ac"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "arxiv",
        "superglue"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.8,
      "provenance_hash": "438868b110b08e60ffc3dca6cfe3f13ab7fafae99317eafefe763b1a3c70df0d"
    },
    {
      "model_id": "bigscience/bloomz-1b7",
      "scanned_at": "2026-07-15T02:03:39.622242Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "uggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "split: validation       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094     metrics:     - type: Ac"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "arxiv",
        "superglue"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.8,
      "provenance_hash": "56e036bb6758c790e3142fc528f9b88caf44f76bf6a57cadcb3cafe82057b7e2"
    },
    {
      "model_id": "bigscience/bloomz-3b",
      "scanned_at": "2026-07-15T02:03:42.387286Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "uggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "split: validation       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094     metrics:     - type: Ac"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "arxiv",
        "superglue"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.8,
      "provenance_hash": "3df7ae887a4f1e7a67f779dfe31fb53105ac3604797b2d79d507c57bd8fef5ca"
    },
    {
      "model_id": "bigscience/bloomz-7b1",
      "scanned_at": "2026-07-15T02:03:45.144223Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "uggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "split: validation       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094     metrics:     - type: Ac"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "arxiv",
        "superglue"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.8,
      "provenance_hash": "92ea78113fcf5d73bab398552a160284d373edbc95e70df03eb7f67760672ede"
    },
    {
      "model_id": "bigscience/bloomz-7b1-mt",
      "scanned_at": "2026-07-15T02:03:47.909549Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3mt",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3mt"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "uggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "split: validation       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094     metrics:     - type: Ac"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "bigscience/xP3mt",
        "bigscience/evaluation-results"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "arxiv",
        "superglue"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.8,
      "provenance_hash": "314c088abea2f1298802e8381f101bf50b939a7c6918a67d0a8d78e66aab7f09"
    },
    {
      "model_id": "bigscience/bloomz-7b1-p3",
      "scanned_at": "2026-07-15T02:03:50.684709Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "Muennighoff/P3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:Muennighoff/P3"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "uggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "split: validation       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094     metrics:     - type: Ac"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "Muennighoff/P3",
        "bigscience/evaluation-results"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "arxiv",
        "superglue"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.8,
      "provenance_hash": "9fb50e577aa4439ab44932a61782fefa65a8e56001aae579964b267bb6fb59b3"
    },
    {
      "model_id": "bigscience/bloomz-mt",
      "scanned_at": "2026-07-15T02:03:53.448655Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3mt",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3mt"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "uggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "split: validation       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094     metrics:     - type: Ac"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "bigscience/xP3mt",
        "bigscience/evaluation-results"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "arxiv",
        "superglue"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.8,
      "provenance_hash": "bc3a42f47987cf0ca1641632f72d0749b8fcd75496d3f62b8a5f1a1ad4c075fe"
    },
    {
      "model_id": "bigscience/bloomz-p3",
      "scanned_at": "2026-07-15T02:03:56.396097Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "Muennighoff/P3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:Muennighoff/P3"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "uggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "split: validation       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094     metrics:     - type: Ac"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "Muennighoff/P3",
        "bigscience/evaluation-results"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "arxiv",
        "superglue"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.8,
      "provenance_hash": "69718f0b39208e39c5f7ab73ca651e040c4db8f20730755a686d46743a61df55"
    },
    {
      "model_id": "bigscience/bloomz-petals",
      "scanned_at": "2026-07-15T02:03:59.168526Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "f0645a80e9f0327c79e023865c926f573e8b2d1873ac48b2a2cd6316a5ea8e6c"
    },
    {
      "model_id": "bigscience/distill-bloom-1b3",
      "scanned_at": "2026-07-15T02:04:01.950781Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "75506b8ae9b9cffa02047e9d46dafa7bb1c72ebf44fda4f2d02a0ab14643c063"
    },
    {
      "model_id": "bigscience/distill-bloom-1b3-10x",
      "scanned_at": "2026-07-15T02:04:04.766496Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mple pre-tokenization rule, no normalization  - A vocabulary size of 250,680  It was trained on a subse"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "dified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https:"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.5,
      "provenance_hash": "65f32d4dd0a0b04b8703533d92b964c9a6817663c0d9e911188012175b48ffc5"
    },
    {
      "model_id": "bigscience/internal-states-peek",
      "scanned_at": "2026-07-15T02:04:07.524999Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b461c722378517e399bf30bc60ce4837fe4c9433e9689895651cec3459778732"
    },
    {
      "model_id": "bigscience/misc-test-data",
      "scanned_at": "2026-07-15T02:04:10.290399Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "5e2bebc88b2345dc017d42e7ffb414270b3a0388b900fec4030b8190ef706b93"
    },
    {
      "model_id": "bigscience/mt0-base",
      "scanned_at": "2026-07-15T02:04:13.089342Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "mc4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:mc4"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.6,
          "raw_context": "f](mailto:niklas@hf.co) - **Languages:** Refer to [mc4](https://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.c"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "google/mt5-base",
          "confidence": 0.9,
          "raw_context": "_name_or_path: google/mt5-base"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "mt5",
          "confidence": 0.5,
          "raw_context": "model_type: mt5"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "mc4",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "mc4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "e7dabdb0a4f205e03493fa5d7744e6f1d6aa0ac7dece3e76fa760fa7f6b16987"
    },
    {
      "model_id": "bigscience/mt0-large",
      "scanned_at": "2026-07-15T02:04:15.855641Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "mc4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:mc4"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.6,
          "raw_context": "f](mailto:niklas@hf.co) - **Languages:** Refer to [mc4](https://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.c"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "google/mt5-large",
          "confidence": 0.9,
          "raw_context": "_name_or_path: google/mt5-large"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "mt5",
          "confidence": 0.5,
          "raw_context": "model_type: mt5"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "mc4",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "mc4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "8702960ba0382feb3ab1cbc9c554750d60a1e989d3aa11e9299a8c5a6e025e01"
    },
    {
      "model_id": "bigscience/mt0-small",
      "scanned_at": "2026-07-15T02:04:18.624281Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "mc4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:mc4"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.6,
          "raw_context": "f](mailto:niklas@hf.co) - **Languages:** Refer to [mc4](https://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.c"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xP3",
          "confidence": 0.6,
          "raw_context": "://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportion"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "google/mt5-small",
          "confidence": 0.9,
          "raw_context": "_name_or_path: google/mt5-small"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "mt5",
          "confidence": 0.5,
          "raw_context": "model_type: mt5"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "mc4",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "mc4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "57c7733eb88a166a1c045041cef8c23e6ec3b11b90e3df4981267fc425a0fd36"
    },
    {
      "model_id": "bigscience/mt0-xl",
      "scanned_at": "2026-07-15T02:04:21.429723Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "mc4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:mc4"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.6,
          "raw_context": "f](mailto:niklas@hf.co) - **Languages:** Refer to [mc4](https://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.c"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "google/mt5-xl",
          "confidence": 0.9,
          "raw_context": "_name_or_path: google/mt5-xl"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "mt5",
          "confidence": 0.5,
          "raw_context": "model_type: mt5"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "mc4",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "mc4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "5b8c029393c6ced101fc55c6033287c34b706306cb50513c1f8863d34c5d7a42"
    },
    {
      "model_id": "bigscience/mt0-xxl",
      "scanned_at": "2026-07-15T02:04:24.282776Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "mc4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:mc4"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.6,
          "raw_context": "f](mailto:niklas@hf.co) - **Languages:** Refer to [mc4](https://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.c"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "google/mt5-xxl",
          "confidence": 0.9,
          "raw_context": "_name_or_path: google/mt5-xxl"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "mt5",
          "confidence": 0.5,
          "raw_context": "model_type: mt5"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "mc4",
        "bigscience/xP3"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "mc4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "13862f106a4edc45d0c7a7596999d1fd90df495c9aa8c9afa9fcb1096145e02a"
    },
    {
      "model_id": "bigscience/mt0-xxl-mt",
      "scanned_at": "2026-07-15T02:04:27.086799Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bigscience/xP3mt",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bigscience/xP3mt"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "mc4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:mc4"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.6,
          "raw_context": "f](mailto:niklas@hf.co) - **Languages:** Refer to [mc4](https://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.c"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3mt - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - bigscience/xP3mt - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "google/mt5-xxl",
          "confidence": 0.9,
          "raw_context": "_name_or_path: google/mt5-xxl"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "mt5",
          "confidence": 0.5,
          "raw_context": "model_type: mt5"
        }
      ],
      "declared_datasets": [
        "bigscience/evaluation-results",
        "bigscience/xP3mt",
        "mc4"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "mc4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "9cac4481740f249236d0b9a14fbbc21a2da13369fcffc250b71c4f50267a310e"
    },
    {
      "model_id": "bigscience/mt0-xxl-p3",
      "scanned_at": "2026-07-15T02:04:29.853044Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "Muennighoff/P3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:Muennighoff/P3"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "mc4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:mc4"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.6,
          "raw_context": "f](mailto:niklas@hf.co) - **Languages:** Refer to [mc4](https://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.c"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "bigscience/evaluation-results",
          "confidence": 0.8,
          "raw_context": "m our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot resul"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - Muennighoff/P3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "language inference     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "superglue",
          "confidence": 0.7,
          "raw_context": "e     dataset:       type: super_glue       name: SuperGLUE (cb)       config: cb       split: validation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eralization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Nikl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "mc4",
          "confidence": 0.7,
          "raw_context": "--- datasets: - Muennighoff/P3 - mc4 license: apache-2.0 language: - af - am - ar - az"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "google/mt5-xxl",
          "confidence": 0.9,
          "raw_context": "_name_or_path: google/mt5-xxl"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "mt5",
          "confidence": 0.5,
          "raw_context": "model_type: mt5"
        }
      ],
      "declared_datasets": [
        "Muennighoff/P3",
        "bigscience/evaluation-results",
        "mc4"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "superglue",
        "mc4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "bb72bfb6cea06fccd19ecf9fb0ecbfb7af792e0329aa62cb789e0952369ec1f8"
    },
    {
      "model_id": "bigscience/oscar_13_languages_alpha_weight",
      "scanned_at": "2026-07-15T02:04:32.667967Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "7996267f6a82d51634d1038e91434932da73d17aed1397b6ff90fa62e448dcdf"
    },
    {
      "model_id": "bigscience/oscar_13_languages_equal_weight",
      "scanned_at": "2026-07-15T02:04:35.422636Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b1035067e42aeb489ff439fa6aa6da58ac23359858a2e790e58cd5e2acdeb8f5"
    },
    {
      "model_id": "bigscience/sgpt-bloom-7b1-msmarco",
      "scanned_at": "2026-07-15T02:04:38.189360Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "revision: 4d853f94cd57d85ec13805aeeac3ae3e5eb4c49c     metrics:     - type: map       value: 59.97"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "type: Clustering     dataset:       type: mteb/arxiv-clustering-p2p       name: MTEB ArxivClusteringP2"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3/bloom-7b1",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3/bloom-7b1"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.4,
      "provenance_hash": "ae5657de955598918b8fa2d1b88ff2fdc9e0799e38181bf3dd2cdfcc18305895"
    },
    {
      "model_id": "bigscience/t5x-cd-flm-logs",
      "scanned_at": "2026-07-15T02:04:41.058461Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "bf743e5e3dc752dce4fe8418fd4252387437c8cd21937aa536ce36f7c15aa30c"
    },
    {
      "model_id": "bigscience/t5x-cd-sc-logs",
      "scanned_at": "2026-07-15T02:04:43.827955Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b2b073d301e7941a2568501a25617d5b52736bd59257418820275295e7ae82cd"
    },
    {
      "model_id": "bigscience/t5x-ed-plm-logs",
      "scanned_at": "2026-07-15T02:04:46.589278Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "e253e9901606bc6c90271cff9381c9d0de941a054f61e32fdaab2455fce65caf"
    },
    {
      "model_id": "bigscience/t5x-ed-sc-logs",
      "scanned_at": "2026-07-15T02:04:49.352940Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "e7256c56584edcf032a86e0ad9884f457271c3d1523f85cb9dd72bdf3a8b9ef1"
    },
    {
      "model_id": "bigscience/t5x-ncd-plm-logs",
      "scanned_at": "2026-07-15T02:04:52.107621Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "1d6c94b34df21dc56824b28f1b3ce7628df2ef0ef30524eadc58de43a5619a7f"
    },
    {
      "model_id": "bigscience/t5x-ncd-sc-logs",
      "scanned_at": "2026-07-15T02:04:54.865909Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "1a15942b10a8f0353c6e35d1244bb8e267433da8fc8d62e71b6216efa51bc623"
    },
    {
      "model_id": "bigscience/t5x-ncd_sc-adapt-cd_flm-logs",
      "scanned_at": "2026-07-15T02:04:57.632673Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "af26fe4ca3378d0bb5df42ac090c52599b5d45edb1b501d763bdf38d550473ab"
    },
    {
      "model_id": "bigscience/test-bloomd",
      "scanned_at": "2026-07-15T02:05:00.392503Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "53fb7fe2547c13a6b34a90ffa5b916c114627f679f876cbc60cd6169167a101a"
    },
    {
      "model_id": "bigscience/test-bloomd-6b3",
      "scanned_at": "2026-07-15T02:05:03.238823Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "41e9244dfd4d51d62ca1db87917feb830e384967438e830bf970582f937ddf31"
    },
    {
      "model_id": "bigscience/test-public",
      "scanned_at": "2026-07-15T02:05:05.988464Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "4cb2d80544ce80851d68cd579bdb12b58de0360f39295ff35f11c834d2994d21"
    },
    {
      "model_id": "bigscience/test-tensorboard",
      "scanned_at": "2026-07-15T02:05:08.740207Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "ca9d1325ff5ab973c5b8bf61bb18aee615f34e813e9a2973b63d3bbb18ab5711"
    },
    {
      "model_id": "bigscience/tr1-13B-checkpoints",
      "scanned_at": "2026-07-15T02:05:11.498854Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "4dc74c2610ed7dbc2329cfc021a71a7c81bf7f8b4e34553319094ef719f9722b"
    },
    {
      "model_id": "bigscience/tr1-13B-codecarbon",
      "scanned_at": "2026-07-15T02:05:14.232353Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "3b6cdb8a9527a10bbc3ec845d32d06eba30b4207801c39d7184fbd8b7f2b140b"
    },
    {
      "model_id": "bigscience/tr1-13B-data",
      "scanned_at": "2026-07-15T02:05:17.006901Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "oscar",
          "confidence": 0.7,
          "raw_context": "e training steps.  - the corresponding dataset is oscar-en that's on JZ at `$six_ALL_CCFRWORK/datasets-cu"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "oscar"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "18f9ce4278a397a2e71462c71f81d3bee60dd61cf676b67a3e9590009339b17b"
    },
    {
      "model_id": "bigscience/tr1-13B-logs",
      "scanned_at": "2026-07-15T02:05:19.834691Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "6d80dec754725485e6069aed0b3c2310dcc3ad7d623c06244d48c1c60465b702"
    },
    {
      "model_id": "bigscience/tr1-13B-tensorboard",
      "scanned_at": "2026-07-15T02:05:22.591249Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "db55c28274e47611aa789c6f4958f9129b4b77ae4242dc8f92a3a9d2b1025d1f"
    },
    {
      "model_id": "bigscience/tr10-13B-logs",
      "scanned_at": "2026-07-15T02:05:25.459637Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "ac3834c51221c1e6f1eb74fe1df5c9f5da4adf6055d9950a5ecf2f64eeea62ca"
    },
    {
      "model_id": "bigscience/tr12a-1B3-oscar-en-filtered",
      "scanned_at": "2026-07-15T02:05:28.223914Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "c547e75b43965c6a131f13e0e8212f930a46535423d4a743f14e829d476aca44"
    },
    {
      "model_id": "bigscience/tr12a-1B3-oscar-en-filtered-logs",
      "scanned_at": "2026-07-15T02:05:31.020416Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "86d8397ca3abbecc1da467f3884498f5382295f76f206744bdcc4b1143d69e5c"
    },
    {
      "model_id": "bigscience/tr12b-1B3-oscar-en-filtered-dedup",
      "scanned_at": "2026-07-15T02:05:33.828877Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "1cf4c41458ef3997398a4b3d0bd8cbc9d83def3a921b0b1a66d16d4bb3a1ac5a"
    },
    {
      "model_id": "bigscience/tr12b-1B3-oscar-en-filtered-dedup-logs",
      "scanned_at": "2026-07-15T02:05:36.586894Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "5761d29baca800af2e13a570518d9857298a5c99b6962d5d2299af9ef8bd4f6d"
    },
    {
      "model_id": "bigscience/tr12c-1B3-oscar-en-overfiltered-logs",
      "scanned_at": "2026-07-15T02:05:39.346769Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "8bd5784d7e2cedd9807153ad7649bcb907aad455ea2129f3711807a5f82690d5"
    },
    {
      "model_id": "bigscience/tr3-1B3-modeling-baseline-tensorboard",
      "scanned_at": "2026-07-15T02:05:42.105903Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "6468fc2b6424c744031754bea0f0fd19eb641c15edaf25f4196e05d581977be0"
    },
    {
      "model_id": "bigscience/tr3b-760M-modeling-baseline-tensorboard",
      "scanned_at": "2026-07-15T02:05:44.990352Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "5f6523c930814b30ec156fe58ac23dbb7b32252191c9e88521444c7451a13ab8"
    },
    {
      "model_id": "bigscience/tr3c-350M-modeling-baseline-tensorboard",
      "scanned_at": "2026-07-15T02:05:47.764426Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "734f00efc00b6be4ea389f3ec10edd65be1008bab74482018b14b521e7bd998f"
    },
    {
      "model_id": "bigscience/tr3d-1B3-more-warmup-tensorboard",
      "scanned_at": "2026-07-15T02:05:50.528998Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "ec9faecaaa36cdc2c5a41f4777eba6cc61613b222f50887a7fe022567e18660d"
    },
    {
      "model_id": "bigscience/tr3d-1B3-oscar-300B-logs",
      "scanned_at": "2026-07-15T02:05:53.284678Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "3de95eb0f771f125fced9d7995d09ed600a308eaea06f43aca9e5830f8dab7c4"
    },
    {
      "model_id": "bigscience/tr3d-1B3-oscar-checkpoints",
      "scanned_at": "2026-07-15T02:05:56.059349Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "0748cfe20be79b6f1ec6ba10ea0bbdf1392af21c1a43d12a0ebe507d16ae4fbf"
    },
    {
      "model_id": "bigscience/tr3e-1B3-c4-300B-logs",
      "scanned_at": "2026-07-15T02:05:58.858260Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "0143ffe2201121653ce33ae2c1eacd206ee6909fba1cc41a6cb0d54b4c0fedaf"
    },
    {
      "model_id": "bigscience/tr3e-1B3-c4-checkpoints",
      "scanned_at": "2026-07-15T02:06:01.608911Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "f132887f7c866c3118b53daf18fef3f2eab6a70303fff39f43ad92b52b90ebb6"
    },
    {
      "model_id": "bigscience/tr3e-1B3-diagnostic1-warmup-c4-tensorboard",
      "scanned_at": "2026-07-15T02:06:04.510905Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "890ea2722f2d928b4462183ce9783e4e4adbcca7d6cda93ed1e50d0f70a2b55c"
    },
    {
      "model_id": "bigscience/tr3f-1B3-diagnostic2-low-warmup-oscar-tensorboard",
      "scanned_at": "2026-07-15T02:06:07.327938Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "d29c451030c74f0e959afd7c63a6083f90a2674788c921e518aca1d46bcd1649"
    },
    {
      "model_id": "bigscience/tr3g-760M-v2-tensorboard",
      "scanned_at": "2026-07-15T02:06:10.081088Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "e80513bca88fee92f51c1e771d0cba4cc83a987da215bd6405b74a472cd3c7c7"
    },
    {
      "model_id": "bigscience/tr3h-350M-oscar-checkpoints",
      "scanned_at": "2026-07-15T02:06:12.856216Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "1414384a3d2d49954a0cb23b1356a2ec7e81e5bff2b96a7ebed4820a31832609"
    },
    {
      "model_id": "bigscience/tr3h-350M-v2-tensorboard",
      "scanned_at": "2026-07-15T02:06:15.612071Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "8d9f8e732c427a44867374d45e66eb15c70716a7184c16ddeee220c0b2f4b372"
    },
    {
      "model_id": "bigscience/tr3i-125M-v2-tensorboard",
      "scanned_at": "2026-07-15T02:06:18.370711Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "ae0ba0149f13be04534ddf60b458dd07a2bd95ddf4fed770492f86f8532b0ab1"
    },
    {
      "model_id": "bigscience/tr3j-760M-pile-tensorboard",
      "scanned_at": "2026-07-15T02:06:21.213418Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "afe322e38defef0909347f4613d275dcff9136a55b829fad3bf06a44c8f47e35"
    },
    {
      "model_id": "bigscience/tr3k-350M-pile-tensorboard",
      "scanned_at": "2026-07-15T02:06:23.972369Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "d93657f3bf5572e160bbcdd980c1501996263b926820f800c2f5d89be2afbaac"
    },
    {
      "model_id": "bigscience/tr3l-125M-pile-tensorboard",
      "scanned_at": "2026-07-15T02:06:26.854262Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "d3fb898df36edf61f7f64576feab8079465ab2bb799480a23e6ccaf9311c1cbf"
    },
    {
      "model_id": "bigscience/tr3m-1B3-emb-norm-pile-logs",
      "scanned_at": "2026-07-15T02:06:29.619607Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "4c744fc6291827c90a2c77b985827bf5427c0055408ebec30b0d9a3d43405fe6"
    },
    {
      "model_id": "bigscience/tr3m-1B3-pile-checkpoints",
      "scanned_at": "2026-07-15T02:06:32.373285Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "164affbe099d91216b3b77c36de1d21add1dc61d27272ad32d0f2d0d027db45f"
    },
    {
      "model_id": "bigscience/tr3m-1B3-pile-tensorboard",
      "scanned_at": "2026-07-15T02:06:35.150308Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "73438e834bbc0c807ec2271f754e2b0e872f730fee404a1bee4717bf238d7884"
    },
    {
      "model_id": "bigscience/tr3n-1B3-pile-fancy-checkpoints",
      "scanned_at": "2026-07-15T02:06:37.987766Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "25c33eb521b427a7872361abd74ddbe6b24d475c8ffeedfbbf37a603740e296d"
    },
    {
      "model_id": "bigscience/tr3n-1B3-pile-fancy-logs",
      "scanned_at": "2026-07-15T02:06:40.737663Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "e034cf6ff2fa0e408dd02c32da1f51ba16b1881e1621261dbda6088ffcbe5bda"
    },
    {
      "model_id": "bigscience/tr3o-1B3-pile-no-dropout-checkpoints",
      "scanned_at": "2026-07-15T02:06:43.492418Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "92435625ebd323052beb9d568dfc8362d40ae796c0d91d3a0399bdf39f2ec820"
    },
    {
      "model_id": "bigscience/tr3o-1B3-pile-no-dropout-logs",
      "scanned_at": "2026-07-15T02:06:46.247032Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "89aaca6ee6b2aaa063043ca73f9e820778e41208e9e668f7bac47dfaa29693e4"
    },
    {
      "model_id": "bigscience/tr4-1B3-rotary-logs",
      "scanned_at": "2026-07-15T02:06:49.000652Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "58bc94fe7c853236966dfa5ffff4c1f0fc2bc8bae9b0f04aa2bc2dd1d747bf3b"
    },
    {
      "model_id": "bigscience/tr4-1B3-rotary-tensorboard",
      "scanned_at": "2026-07-15T02:06:51.797752Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "a0ac150e55c40596d15c965b5b22669f9eb49f2e32ed2c64b1258107d21b9cce"
    },
    {
      "model_id": "bigscience/tr4b-350M-tensorboard",
      "scanned_at": "2026-07-15T02:06:54.554148Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "2e40e7e6a006afac09cf74ae13418be58057127ec2efa834acd6a20fcf0297b8"
    },
    {
      "model_id": "bigscience/tr4c-1B3-rotary-oscar-checkpoints",
      "scanned_at": "2026-07-15T02:06:57.390378Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "32feb529caa8739d4a7dbb9981b50f1216076941745679e405a437533165b4f8"
    },
    {
      "model_id": "bigscience/tr4c-1B3-rotary-oscar-logs",
      "scanned_at": "2026-07-15T02:07:00.148139Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "7c1d8bfc00cfc6a27c6894f87d19a03b3446a4c73a7fae7a34a6737b385860a2"
    },
    {
      "model_id": "bigscience/tr5a-1B3-multilingual-mt5tok-checkpoints",
      "scanned_at": "2026-07-15T02:07:02.978360Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "81676964f1e09c705f062af59a15116ca5111864a6a532f53b69c8716ca1c1ae"
    },
    {
      "model_id": "bigscience/tr5a-1B3-multilingual-mt5tok-logs",
      "scanned_at": "2026-07-15T02:07:05.740812Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "be33533dbab74c60e873c104296e2309570302851c6b61ddf41e3e02fe35180c"
    },
    {
      "model_id": "bigscience/tr5b-1B3-multilingual-alpha-checkpoints",
      "scanned_at": "2026-07-15T02:07:08.586052Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "99f9507fc46ef1d07c3c3657b31f0f866b10513fb6f73d40d5cfedc095d5ccea"
    },
    {
      "model_id": "bihungba1101/Deep-Artic-v1-1B",
      "scanned_at": "2026-07-15T02:07:11.409898Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "c454873faa8d15035067f667ae6907cd83a5ce86971f26d9a53553580f6e51d4"
    },
    {
      "model_id": "bihungba1101/Deep-Artic-v1-90M",
      "scanned_at": "2026-07-15T02:07:14.140325Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "38617e5c60f1b91abcd454d7757c704514c74c5a5694b38cdd71a9550290a6c6"
    },
    {
      "model_id": "biswasagnij2004/gpt2-medium-dpo-ft",
      "scanned_at": "2026-07-15T02:07:16.868335Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).  - **Hardware Type:** [More"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.35,
      "provenance_hash": "7c75d2e6680e5cc5a01da68d26f690692ca66f397a542c32824fef55b4a3575f"
    },
    {
      "model_id": "black-forest-labs/FLUX.2-dev-NVFP4",
      "scanned_at": "2026-07-15T02:07:19.629223Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "0eb24c4972e08b76ce9c174a696d6115e75f1a28dc39bc2581da1345a669f435"
    },
    {
      "model_id": "black-forest-labs/FLUX.2-klein-9B",
      "scanned_at": "2026-07-15T02:07:22.372849Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "3fea88e51a9bae145f606b2dd93174189b971adf961a800ad4d4d359bc81fb3f"
    },
    {
      "model_id": "black-forest-labs/FLUX.2-klein-9b-fp8",
      "scanned_at": "2026-07-15T02:07:25.105213Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "7aa010e03505c8e3c79877351c561518ff0bf1335e262a338f8abd158cd9a1f5"
    },
    {
      "model_id": "black-forest-labs/FLUX.2-klein-9b-nvfp4",
      "scanned_at": "2026-07-15T02:07:27.832349Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "774a2e862321154ba4a0851fdfc26989f684095c2e93a9c7ab9649feb9b5f513"
    },
    {
      "model_id": "black-forest-labs/FLUX.2-klein-base-4B",
      "scanned_at": "2026-07-15T02:07:30.564574Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.1,
      "provenance_hash": "f2a32658301f9b3d7d7db718d059393799c6d2d1c13a68ae52cb1f4d425c4ebf"
    },
    {
      "model_id": "black-forest-labs/FLUX.2-klein-base-4b-fp8",
      "scanned_at": "2026-07-15T02:07:33.315433Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.1,
      "provenance_hash": "f359cdd4d859d0476ff0f2ad47390c420abbe54d355c2c080ca835399569c596"
    },
    {
      "model_id": "black-forest-labs/FLUX.2-klein-base-4b-nvfp4",
      "scanned_at": "2026-07-15T02:07:36.159597Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.1,
      "provenance_hash": "7f5b8be65a1468b7591e145d618e163c08616fad7e7e55f8a35c46be718c30fa"
    },
    {
      "model_id": "black-forest-labs/FLUX.2-klein-base-9B",
      "scanned_at": "2026-07-15T02:07:38.972812Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "353be13fd48cdb79c4c641a495716cb07783ebb9750098e88ca8662b6b5a2aab"
    },
    {
      "model_id": "black-forest-labs/FLUX.2-klein-base-9b-fp8",
      "scanned_at": "2026-07-15T02:07:41.704722Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "e2dfc846bcce09f37b8731d12d709c097de4216b71825642c2b2b98e4c961a56"
    },
    {
      "model_id": "bonekung/amksmadasd",
      "scanned_at": "2026-07-15T02:07:44.440021Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "ecl-2.0",
      "provenance_score": 0.1,
      "provenance_hash": "b34712dd7cf4147c42d5c6745506cd1ed8c8aa9199733e1bfc210eaf7e94340e"
    },
    {
      "model_id": "bookbot/distil-ast-audioset",
      "scanned_at": "2026-07-15T02:07:47.202277Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ed on the [Audio Spectrogram Transformer](https://arxiv.org/abs/2104.01778) architecture. This model is a"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "MIT/ast-finetuned-audioset-10-10-0.4593",
          "confidence": 0.9,
          "raw_context": "_name_or_path: MIT/ast-finetuned-audioset-10-10-0.4593"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "audio-spectrogram-transformer",
          "confidence": 0.5,
          "raw_context": "model_type: audio-spectrogram-transformer"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.45,
      "provenance_hash": "94b3189e0397c6241ab724e50661f08bd6c7f715adf75e9672e69dc1c646111e"
    },
    {
      "model_id": "bragour/Camel-7b-chat",
      "scanned_at": "2026-07-15T02:07:49.953095Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "bragour/Palestinian_Truth_English",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:bragour/Palestinian_Truth_English"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "NousResearch/Llama-2-7b-chat-hf",
          "confidence": 0.9,
          "raw_context": "_name_or_path: NousResearch/Llama-2-7b-chat-hf"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [
        "bragour/Palestinian_Truth_English"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "llama2",
      "provenance_score": 0.2,
      "provenance_hash": "c99a5c8c86cb0e361a00d20dc9cff6c70f9471fd9c573e4dfd03b5bc386f26ab"
    },
    {
      "model_id": "branague01/3ybvyf39",
      "scanned_at": "2026-07-15T02:07:52.745225Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "461a350aa9ceb58cabd7a5f139d4da688e0a34639107fc0a81b537e442d9943a"
    },
    {
      "model_id": "breezedeus/pix2text-mfd",
      "scanned_at": "2026-07-15T02:07:55.524013Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.1,
      "provenance_hash": "75f9706624536fd171083570787257a91a2142759a0e5f6b063c4784bb2d23bd"
    },
    {
      "model_id": "breezedeus/pix2text-mfr-1.5",
      "scanned_at": "2026-07-15T02:07:58.285406Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "vision-encoder-decoder",
          "confidence": 0.5,
          "raw_context": "model_type: vision-encoder-decoder"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.1,
      "provenance_hash": "ec4b7046fc8f94727bc7032d6964ee23d96968d789b2364ee4bbb8249eb6b11b"
    },
    {
      "model_id": "breezedeus/pix2text-table-rec",
      "scanned_at": "2026-07-15T02:08:01.033916Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "datasets for table structure recognition](https://arxiv.org/abs/2303.00716) by Smock et al. and first rel"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "table-transformer",
          "confidence": 0.5,
          "raw_context": "model_type: table-transformer"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "38bc2fcbacc87ecd5755f141eace9d836e4c7c4b3d526c94e6fd4c171d0cc130"
    },
    {
      "model_id": "briaai/Fibo-Edit",
      "scanned_at": "2026-07-15T02:08:03.792101Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "briaai/Fibo-Edit",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:briaai/Fibo-Edit"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:briaai/Fibo-Edit",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:briaai/Fibo-Edit"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "1c3a6a33731a137e67b5cae52023d6fc8d13d941c95e15402d332af132721cae"
    },
    {
      "model_id": "brikdavies/LN-Nano8B-lenpen",
      "scanned_at": "2026-07-15T02:08:06.631830Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "llama3.1",
      "provenance_score": 0.1,
      "provenance_hash": "eb2da67efddd5268b9e7cc78413b68db674edbca579d23893b4c4bd95279e769"
    },
    {
      "model_id": "bullerwins/FLUX.1-Kontext-dev-GGUF",
      "scanned_at": "2026-07-15T02:08:09.433200Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "black-forest-labs/FLUX.1-Kontext-dev",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:black-forest-labs/FLUX.1-Kontext-dev"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:black-forest-labs/FLUX.1-Kontext-dev",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:black-forest-labs/FLUX.1-Kontext-dev"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "1-kontext-dev) and our [technical report](https://arxiv.org/abs/2506.15742). You can find information abo"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "black-forest-labs/FLUX.1-Kontext-dev",
      "base_model_chain": [
        "black-forest-labs/FLUX.1-Kontext-dev"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.25,
      "provenance_hash": "b2db6d3a1be326f0a5f11eee2fb1a6e87ca2ae55d7997319967c8dd02249fc10"
    },
    {
      "model_id": "burcusu/videomae-base-finetuned-ucf101-subset",
      "scanned_at": "2026-07-15T02:08:14.008873Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "MCG-NJU/videomae-base",
          "confidence": 0.9,
          "raw_context": "_name_or_path: MCG-NJU/videomae-base"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "videomae",
          "confidence": 0.5,
          "raw_context": "model_type: videomae"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "cc-by-nc-4.0",
      "provenance_score": 0.4,
      "provenance_hash": "6ceea719a286801b981af588f78502defbd0a3e6d290d7d1792d8d080582621d"
    },
    {
      "model_id": "bvallegc/wav2vec2_spoof_dection1-finetuned-spoofing-classifier",
      "scanned_at": "2026-07-15T02:08:16.767279Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "WWWxp/wav2vec2_spoof_dection1",
          "confidence": 0.9,
          "raw_context": "_name_or_path: WWWxp/wav2vec2_spoof_dection1"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "wav2vec2",
          "confidence": 0.5,
          "raw_context": "model_type: wav2vec2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "413c7686dd84f71bc5c8aecc4d24b7dfbb798ccecb9055e76434060016149d87"
    },
    {
      "model_id": "bwittmann/vesselFM",
      "scanned_at": "2026-07-15T02:08:19.526257Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "our three proposed",
          "confidence": 0.6,
          "raw_context": "ckpoints:  - `vesselFM_base.pt`: VesselFM variant pre-trained on our three proposed data sources (D_real, D_drand, and D_flow). This check"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "56ec4e2e1c34dcc8355055648dd5c6be2f7c5787df0edeacc61433d56a3bfc9d"
    },
    {
      "model_id": "c1772561859/mature-illustrious-v10-v10-sdxl",
      "scanned_at": "2026-07-15T02:08:22.318846Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "OnomaAIResearch/Illustrious-xl-early-release-v0",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:OnomaAIResearch/Illustrious-xl-early-release-v0"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:OnomaAIResearch/Illustrious-xl-early-release-v0",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:OnomaAIResearch/Illustrious-xl-early-release-v0"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "OnomaAIResearch/Illustrious-xl-early-release-v0",
          "confidence": 0.85,
          "raw_context": "ure ritual\r - Illustrious XL v1.0\r - illustrious\r base_model: OnomaAIResearch/Illustrious-xl-early-release-v0\r ---\r \r Original model is [here](https://civitai."
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:OnomaAIResearch/Illustrious-xl-early-release-v0",
          "value": "Danbooru2023",
          "confidence": 0.48,
          "raw_context": "XL Model</li>       <li><strong>Dataset:</strong> Fine-tuned on Danbooru2023 Dataset</li>     </ul>     <p>       <strong>Description<"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:OnomaAIResearch/Illustrious-xl-early-release-v0",
          "value": "comprehensive Danbooru2023",
          "confidence": 0.48,
          "raw_context": "L</strong> is a powerful generative model series, fine-tuned on the comprehensive Danbooru2023 dataset and its variants. It includes a wide variety of c"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:OnomaAIResearch/Illustrious-xl-early-release-v0",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "oads.huggingface.co/production/uploads/651d27e3a00c49c5e50c0653/RiStls1S26meeu8UV8wKj.png\" alt=\"s23\">"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:OnomaAIResearch/Illustrious-xl-early-release-v0",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "argin-left: 20px;\">         <li> <a href=\"https://arxiv.org/abs/2409.19946\" target=\"_blank\">https://arxiv"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "comprehensive Danbooru2023",
        "Danbooru2023",
        "arxiv"
      ],
      "base_model": "OnomaAIResearch/Illustrious-xl-early-release-v0",
      "base_model_chain": [
        "OnomaAIResearch/Illustrious-xl-early-release-v0",
        "KBlueLeaf/kohaku-xl-beta5"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.4,
      "provenance_hash": "0a7f0787048fc5c5090ea903d45a1d20fc13d31c4ce6301060d3f68c49ce9533"
    },
    {
      "model_id": "cacnhatdoan/QhF2nSTDlREF139",
      "scanned_at": "2026-07-15T02:08:27.969296Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "188103fcc6a99e86b1f692ad8bdb7466b96130ea7cb240ac040a405e3ddee1d7"
    },
    {
      "model_id": "cacnhatdoan/jIwrqpS7o7drzlX",
      "scanned_at": "2026-07-15T02:08:30.705315Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "5c0aa30f74ad5e20806927524e863ea76ec76e961b245ab90aa0bd441c8457bd"
    },
    {
      "model_id": "cacnhatdoan/vgOqAqScuLEnQQL",
      "scanned_at": "2026-07-15T02:08:33.437229Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "ccf7b7f9c7a8b93be653e220ab0001580d102e355f097ab17b3f34a25bb219e4"
    },
    {
      "model_id": "caffeinism/mimi-qwen3-tts-encoder",
      "scanned_at": "2026-07-15T02:08:36.170300Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "mimi",
          "confidence": 0.5,
          "raw_context": "model_type: mimi"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "51ecd7313f67fc7c8727d7dcd9f7e480cfb9702990219623eeea14af55215c42"
    },
    {
      "model_id": "cagataydev/sac-unitree-g1-mujoco",
      "scanned_at": "2026-07-15T02:08:38.943304Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "d20d50e2c6b9392b59fa3ad8b5fbc3fa845c62c15a5af4dc88cb30d0a85c576e"
    },
    {
      "model_id": "cagataydev/sac-unitree-go2-mujoco",
      "scanned_at": "2026-07-15T02:08:41.838559Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "36fb8f3528f74e7c9b44adba43c1122a47e1e2ee60dd26a1095202108152f2c7"
    },
    {
      "model_id": "caidas/swin2SR-realworld-sr-x4-64-bsrgan-psnr",
      "scanned_at": "2026-07-15T02:08:44.595958Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "d Image Super-Resolution and Restoration](https://arxiv.org/abs/2209.11345) by Conde et al. and first rel"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "swin2sr",
          "confidence": 0.5,
          "raw_context": "model_type: swin2sr"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "0573c3aee66472ae43606ec06bc27bdbcd7a88b1314349bd6c7a2c8b965a8636"
    },
    {
      "model_id": "camducthuan85/QYyvFwBjTeJaxoT",
      "scanned_at": "2026-07-15T02:08:47.332757Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "416cf0c15e3a181e7f022aed30c13853dd2e5a8e7de9baa4df7289a003ff5556"
    },
    {
      "model_id": "camducthuan85/ZHbugDdfL7hU14t",
      "scanned_at": "2026-07-15T02:08:50.067537Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "efcdd740dd8928a6f229535fb83d3d2ac28ecd9102b3063a94733c521aed3258"
    },
    {
      "model_id": "camducthuan85/y2Q8n9bWuZ1cGb5",
      "scanned_at": "2026-07-15T02:08:52.792710Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "138e3110078ec7f5b19fd24127639def823a0f9d0ec5144c69b60b13cacf52d6"
    },
    {
      "model_id": "camenduru/RMBG-2.0",
      "scanned_at": "2026-07-15T02:08:55.531106Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "ZhengPeng7/BiRefNet",
          "confidence": 0.9,
          "raw_context": "_name_or_path: ZhengPeng7/BiRefNet"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "other",
      "provenance_score": 0.4,
      "provenance_hash": "6210ebf7f399b29ea187dae544a8ae2afc40010ecc30749f6d1534d538f5c4b6"
    },
    {
      "model_id": "camiellia/llava_fiubench_unlearn_KL_checkpoint_1",
      "scanned_at": "2026-07-15T02:08:58.299702Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).  - **Hardware Type:** [More"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.35,
      "provenance_hash": "f69c6eb8a1d517ab67c5875295fa82823be77b9d58b77a063d45bc99e95fcde5"
    },
    {
      "model_id": "camilablank/all_sl_weights",
      "scanned_at": "2026-07-15T02:09:01.078650Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "3ae4919514a7d64bc3d6709d648da52a6c3c7bcf58fb5f677e9dfde5778ab8f9"
    },
    {
      "model_id": "camvanlanh87/CLjFPzNRdkEuZ3F",
      "scanned_at": "2026-07-15T02:09:03.865674Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "e9e61b61de53b8b880f718469bc6e21baeb6573a83beb7f31a60737b52b6abb7"
    },
    {
      "model_id": "camvanlanh87/odfIsf9wvoDabqh",
      "scanned_at": "2026-07-15T02:09:06.596898Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "49cddbe854143d36020bbb577c45a08fdd01dc8656cb437eb0fa4123513ae881"
    },
    {
      "model_id": "camvanlanh87/pCc1eBXC04dGpG9",
      "scanned_at": "2026-07-15T02:09:09.327061Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "3d5e5252b0ebe0c6242a187fa211a0a1a3143c492fb9fe52519718203791c879"
    },
    {
      "model_id": "canhatdoan/GMC6xJjwP6oIUr9",
      "scanned_at": "2026-07-15T02:09:12.063601Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "6706f5269d7e8648092d8e8e1d18f21d9eec22b88a4072de67151a9df4774445"
    },
    {
      "model_id": "canhatdoan/NpGIK5heYO9chkX",
      "scanned_at": "2026-07-15T02:09:14.793386Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "468b0832ae990b119fd6994d0fc097631843c2dbefb7fa21196e8d33a14835fd"
    },
    {
      "model_id": "canhatdoan/abPVLtA1dMwZSeh",
      "scanned_at": "2026-07-15T02:09:17.528041Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "50d0f9f67d6403b795cd4e5ccd0677f57fd70ea1aed5f4e5ced6ebe37a731fab"
    },
    {
      "model_id": "canopylabs/3b-de-ft-research_release",
      "scanned_at": "2026-07-15T02:09:20.261814Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "canopylabs/orpheus-3b-0.1-pretrained",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:canopylabs/orpheus-3b-0.1-pretrained"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:canopylabs/orpheus-3b-0.1-pretrained",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:canopylabs/orpheus-3b-0.1-pretrained"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "canopylabs/orpheus-3b-0.1-pretrained",
      "base_model_chain": [
        "canopylabs/orpheus-3b-0.1-pretrained",
        "meta-llama/Llama-3.2-3B-Instruct"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "53b4bc56a1dd3dca7d2a8780b360f8ae504cea7fdcfac8963b9dadf46884cf68"
    },
    {
      "model_id": "canopylabs/3b-ko-ft-research_release",
      "scanned_at": "2026-07-15T02:09:25.738701Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "canopylabs/orpheus-3b-0.1-pretrained",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:canopylabs/orpheus-3b-0.1-pretrained"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:canopylabs/orpheus-3b-0.1-pretrained",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:canopylabs/orpheus-3b-0.1-pretrained"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "canopylabs/orpheus-3b-0.1-pretrained",
      "base_model_chain": [
        "canopylabs/orpheus-3b-0.1-pretrained",
        "meta-llama/Llama-3.2-3B-Instruct"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "990d81fe6017ad2fb055194c25c83f8b7073b31852a4217b33e82d575e320c73"
    },
    {
      "model_id": "canopylabs/orpheus-3b-0.1-ft",
      "scanned_at": "2026-07-15T02:09:28.475443Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "canopylabs/orpheus-3b-0.1-pretrained",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:canopylabs/orpheus-3b-0.1-pretrained"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:canopylabs/orpheus-3b-0.1-pretrained",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:canopylabs/orpheus-3b-0.1-pretrained"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "canopylabs/orpheus-3b-0.1-pretrained",
      "base_model_chain": [
        "canopylabs/orpheus-3b-0.1-pretrained",
        "meta-llama/Llama-3.2-3B-Instruct"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "2c351048f8a70212c617113ce4bf0026e9dac8065211f09079adbf6749c14ef3"
    },
    {
      "model_id": "canopylabs/orpheus-3b-0.1-pretrained",
      "scanned_at": "2026-07-15T02:09:31.288812Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "meta-llama/Llama-3.2-3B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:meta-llama/Llama-3.2-3B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:meta-llama/Llama-3.2-3B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:meta-llama/Llama-3.2-3B-Instruct"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "meta-llama/Llama-3.2-3B-Instruct",
      "base_model_chain": [
        "meta-llama/Llama-3.2-3B-Instruct"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "113253c99b622feb9198bc6148e2a05a468bf27db79d579d26457333f49d47b7"
    },
    {
      "model_id": "caothitien259/5UN5GdxTZDyjvk2",
      "scanned_at": "2026-07-15T02:09:33.110687Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "2276ffcc23ce6469ae90dc408b834a73b7f24d078c02dc3379cedacdaffa896e"
    },
    {
      "model_id": "caothitien259/qvIHUVFz3tsAbRn",
      "scanned_at": "2026-07-15T02:09:35.844870Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "ae866125b2dd1446788a007c8833d242f17ed9e930f46f57bfe6cb8750cee89b"
    },
    {
      "model_id": "caothitien259/w5M7duLTHFGbeAa",
      "scanned_at": "2026-07-15T02:09:38.577728Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "4c5900f4446f26a585dfc25de254190991739e1dbab2beefb93a492116998334"
    },
    {
      "model_id": "cartesia/sesame-csm-1b-gguf",
      "scanned_at": "2026-07-15T02:09:41.310913Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "sesame/csm-1b",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:sesame/csm-1b"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:sesame/csm-1b",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:sesame/csm-1b"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "sesame/csm-1b",
      "base_model_chain": [
        "sesame/csm-1b"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "93982caf35062b246d05100f117a38b4ef7c386bc2d4d0fb3436ecf68f69ba25"
    },
    {
      "model_id": "cd2001zxm/t-bert-ner",
      "scanned_at": "2026-07-15T02:09:45.902315Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bert",
          "confidence": 0.5,
          "raw_context": "model_type: bert"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "55b5f36c097d914fa7bbd4a85a946a613e5bc20a69dc323e6a4cd6eccfc4c819"
    },
    {
      "model_id": "cehkop/layoutlmv2-base-uncased_finetuned_docvqa",
      "scanned_at": "2026-07-15T02:09:48.659159Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "microsoft/layoutlmv2-base-uncased",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:microsoft/layoutlmv2-base-uncased"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:microsoft/layoutlmv2-base-uncased",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:microsoft/layoutlmv2-base-uncased"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "microsoft/layoutlmv2-base-uncased",
          "confidence": 0.85,
          "raw_context": "--- license: cc-by-nc-sa-4.0 base_model: microsoft/layoutlmv2-base-uncased tags: - generated_from_trainer model-index: - nam"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/layoutlmv2-base-uncased",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/layoutlmv2-base-uncased"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "layoutlmv2",
          "confidence": 0.5,
          "raw_context": "model_type: layoutlmv2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/layoutlmv2-base-uncased",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "for Visually-Rich Document Understanding](https://arxiv.org/abs/2012.14740) Yang Xu, Yiheng Xu, Tengchao"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "microsoft/layoutlmv2-base-uncased",
      "base_model_chain": [
        "microsoft/layoutlmv2-base-uncased"
      ],
      "training_section_present": true,
      "license": "cc-by-nc-sa-4.0",
      "provenance_score": 0.55,
      "provenance_hash": "cedcc6c61a095ce2af35cd14125a1d054017f2d130487e882ff5ba89ac844869"
    },
    {
      "model_id": "cerebras/Cerebras-GPT-1.3B",
      "scanned_at": "2026-07-15T02:09:53.245994Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "the_pile",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:the_pile"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "both the standard dataset and deduplicated",
          "confidence": 0.6,
          "raw_context": "ata, decreasing the Pile dataset size. Pythia was trained on both the standard dataset and deduplicated dataset to characterize the impact. Our models are traine"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Pile",
          "confidence": 0.6,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "a set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size: 50257 * Sequence Length: 2048 * Opti"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the pile",
          "confidence": 0.7,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)!  ## Mod"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [
        "the_pile"
      ],
      "inferred_datasets": [
        "voc",
        "the pile",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.65,
      "provenance_hash": "bea842937ddc4f996fa560b382dbde9d9d837199cadb457e89cac95f0396f274"
    },
    {
      "model_id": "cerebras/Cerebras-GPT-111M",
      "scanned_at": "2026-07-15T02:09:56.001383Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "the_pile",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:the_pile"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "both the standard dataset and deduplicated",
          "confidence": 0.6,
          "raw_context": "ata, decreasing the Pile dataset size. Pythia was trained on both the standard dataset and deduplicated dataset to characterize the impact. Our models are traine"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Pile",
          "confidence": 0.6,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "a set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size: 50257 * Sequence Length: 2048 * Opti"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the pile",
          "confidence": 0.7,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)!  ## Mod"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [
        "the_pile"
      ],
      "inferred_datasets": [
        "voc",
        "the pile",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.65,
      "provenance_hash": "3ea2c16796bb7fff436be17b68c5f6bc260bcde74bd71b66e1f7e12ad7b23b18"
    },
    {
      "model_id": "cerebras/Cerebras-GPT-13B",
      "scanned_at": "2026-07-15T02:09:58.756274Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "the_pile",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:the_pile"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "both the standard dataset and deduplicated",
          "confidence": 0.6,
          "raw_context": "ata, decreasing the Pile dataset size. Pythia was trained on both the standard dataset and deduplicated dataset to characterize the impact. Our models are traine"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Pile",
          "confidence": 0.6,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "a set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size: 50257 * Sequence Length: 2048 * Opti"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the pile",
          "confidence": 0.7,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)!  ## Mod"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/cb/scrap/cynthia/Cerebras-GPT-13B",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /cb/scrap/cynthia/Cerebras-GPT-13B"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [
        "the_pile"
      ],
      "inferred_datasets": [
        "voc",
        "the pile",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.65,
      "provenance_hash": "f495b2a8e8d585ed9c5a079905cd6eed6fd9c582f890bce9999a5b6a26398627"
    },
    {
      "model_id": "cerebras/Cerebras-GPT-2.7B",
      "scanned_at": "2026-07-15T02:10:01.513047Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "the_pile",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:the_pile"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "both the standard dataset and deduplicated",
          "confidence": 0.6,
          "raw_context": "ata, decreasing the Pile dataset size. Pythia was trained on both the standard dataset and deduplicated dataset to characterize the impact. Our models are traine"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Pile",
          "confidence": 0.6,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "a set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size: 50257 * Sequence Length: 2048 * Opti"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the pile",
          "confidence": 0.7,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)!  ## Mod"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [
        "the_pile"
      ],
      "inferred_datasets": [
        "voc",
        "the pile",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.65,
      "provenance_hash": "f9edf8e81b1299b693230b139eb8c13d7b73094f6f1d726db52a24dac4fd605e"
    },
    {
      "model_id": "cerebras/Cerebras-GPT-256M",
      "scanned_at": "2026-07-15T02:10:04.333261Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "the_pile",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:the_pile"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "both the standard dataset and deduplicated",
          "confidence": 0.6,
          "raw_context": "ata, decreasing the Pile dataset size. Pythia was trained on both the standard dataset and deduplicated dataset to characterize the impact. Our models are traine"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Pile",
          "confidence": 0.6,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "a set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size: 50257 * Sequence Length: 2048 * Opti"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the pile",
          "confidence": 0.7,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)!  ## Mod"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [
        "the_pile"
      ],
      "inferred_datasets": [
        "voc",
        "the pile",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.65,
      "provenance_hash": "3a95a74235c2366c17af955326067b796c52e0d2918e3b930b4dae57f9f091d3"
    },
    {
      "model_id": "cerebras/Cerebras-GPT-590M",
      "scanned_at": "2026-07-15T02:10:07.086060Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "the_pile",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:the_pile"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "both the standard dataset and deduplicated",
          "confidence": 0.6,
          "raw_context": "ata, decreasing the Pile dataset size. Pythia was trained on both the standard dataset and deduplicated dataset to characterize the impact. Our models are traine"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Pile",
          "confidence": 0.6,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "a set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size: 50257 * Sequence Length: 2048 * Opti"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the pile",
          "confidence": 0.7,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)!  ## Mod"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [
        "the_pile"
      ],
      "inferred_datasets": [
        "voc",
        "the pile",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.65,
      "provenance_hash": "818c7d1cba38b5af4e1fceed2bb76dc11416c802d89fb064cba85e31537d1014"
    },
    {
      "model_id": "cerebras/Cerebras-GPT-6.7B",
      "scanned_at": "2026-07-15T02:10:09.866957Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "the_pile",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:the_pile"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "both the standard dataset and deduplicated",
          "confidence": 0.6,
          "raw_context": "ata, decreasing the Pile dataset size. Pythia was trained on both the standard dataset and deduplicated dataset to characterize the impact. Our models are traine"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "The Pile",
          "confidence": 0.6,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "a set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size: 50257 * Sequence Length: 2048 * Opti"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the pile",
          "confidence": 0.7,
          "raw_context": "rchitecture: GPT-3 style architecture * Data set: The Pile * Tokenizer: Byte Pair Encoding * Vocabulary Size"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)!  ## Mod"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [
        "the_pile"
      ],
      "inferred_datasets": [
        "voc",
        "the pile",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.65,
      "provenance_hash": "11f73f1592b293d774fec304b74172eec2f4bfd522c153182dbcf0483f3f4de8"
    },
    {
      "model_id": "cerebras/Cerebras-GPT-Intermediate",
      "scanned_at": "2026-07-15T02:10:12.626810Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "the_pile",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:the_pile"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "the Pile",
          "confidence": 0.6,
          "raw_context": "t of Scope Use Cerebras-GPT models are trained on the Pile, with English language only, and are not suitable"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "the pile",
          "confidence": 0.7,
          "raw_context": "t of Scope Use Cerebras-GPT models are trained on the Pile, with English language only, and are not suitable"
        }
      ],
      "declared_datasets": [
        "the_pile"
      ],
      "inferred_datasets": [
        "the pile"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.25,
      "provenance_hash": "30baf5b60d53013ae5a18275d2e2bb6711510a5eebfd240d02f51abfd2837476"
    },
    {
      "model_id": "cerebras/Cerebras-LLaVA-13B",
      "scanned_at": "2026-07-15T02:10:15.388214Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "various",
          "confidence": 0.6,
          "raw_context": "ained from Vicuna-13B checkpoints and instruction finetuned on various datasets. * Projector: the projector module that connects"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "sharegpt",
          "confidence": 0.7,
          "raw_context": "at [cerebras/Cerebras-ViT-L-336-patch14-llava13b-ShareGPT4V](https://huggingface.co/cerebras/Cerebras-ViT-L"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llava",
          "confidence": 0.5,
          "raw_context": "model_type: llava"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "sharegpt"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "bb9c40b4d17c28567cc1a69225860b93383e926b1134267ae18946d6312c74ae"
    },
    {
      "model_id": "cerebras/Cerebras-LLaVA-7B",
      "scanned_at": "2026-07-15T02:10:18.137844Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "various",
          "confidence": 0.6,
          "raw_context": "rained from Vicuna-7B checkpoints and instruction finetuned on various datasets. * Projector: the projector module that connects"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "sharegpt",
          "confidence": 0.7,
          "raw_context": "d at [cerebras/Cerebras-ViT-L-336-patch14-llava7b-ShareGPT4V](https://huggingface.co/cerebras/Cerebras-ViT-L"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llava",
          "confidence": 0.5,
          "raw_context": "model_type: llava"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "sharegpt"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "d3b7e26fd60a69a9dba63d126e7395daa5cd4f9ed495da35411572de195c2ba1"
    },
    {
      "model_id": "cerebras/Cerebras-ViT-L-336-patch14-llava13b-ShareGPT4V",
      "scanned_at": "2026-07-15T02:10:20.889463Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "sharegpt",
          "confidence": 0.7,
          "raw_context": "odel Card for Cerebras-ViT-L-336-patch14-llava13b-ShareGPT4V The checkpoints here are for the vision encoder"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "clip_vision_model",
          "confidence": 0.5,
          "raw_context": "model_type: clip_vision_model"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "sharegpt"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "fb7af85ae5c84aa1a842300185d224cc5ecbf60b9f96e0a46e32a051ba336ad2"
    },
    {
      "model_id": "cerebras/Cerebras-ViT-L-336-patch14-llava7b-ShareGPT4V",
      "scanned_at": "2026-07-15T02:10:23.642095Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "sharegpt",
          "confidence": 0.7,
          "raw_context": "Model Card for Cerebras-ViT-L-336-patch14-llava7b-ShareGPT4V The checkpoints here are for the vision encoder"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "clip_vision_model",
          "confidence": 0.5,
          "raw_context": "model_type: clip_vision_model"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "sharegpt"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "9b7e69fa96d51b3dc8897b1505305e10e0f22e043382a585a062fa15bf567b01"
    },
    {
      "model_id": "cerebras/DeepSeek-V3.2-REAP-345B-A37B",
      "scanned_at": "2026-07-15T02:10:26.395517Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepseek-ai/DeepSeek-V3.2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepseek-ai/DeepSeek-V3.2"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:deepseek-ai/DeepSeek-V3.2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:deepseek-ai/DeepSeek-V3.2"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v3",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v3"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-V3.2",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "deepseek-ai/DeepSeek-V3.2",
      "base_model_chain": [
        "deepseek-ai/DeepSeek-V3.2",
        "deepseek-ai/DeepSeek-V3.2-Exp-Base"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "fc697778a14bbd552c60df1595633024ef355ec8636c873b730cfd18bf218d46"
    },
    {
      "model_id": "cerebras/DeepSeek-V3.2-REAP-508B-A37B",
      "scanned_at": "2026-07-15T02:10:31.920255Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepseek-ai/DeepSeek-V3.2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepseek-ai/DeepSeek-V3.2"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:deepseek-ai/DeepSeek-V3.2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:deepseek-ai/DeepSeek-V3.2"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v3",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v3"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-V3.2",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "deepseek-ai/DeepSeek-V3.2",
      "base_model_chain": [
        "deepseek-ai/DeepSeek-V3.2",
        "deepseek-ai/DeepSeek-V3.2-Exp-Base"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "629e814ca796eb88328dc96e15fb4b8ad6422ed1619e00b3329fec3df82e84db"
    },
    {
      "model_id": "cerebras/Dragon-DocChat-Context-Encoder",
      "scanned_at": "2026-07-15T02:10:34.679801Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.6,
          "raw_context": "</tbody> </table>  \\*Evaluated on a subset of the wikipedia corpus that was available to us. All models use t"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ds Generalizable Dense Retrieval, \turl = {https://arxiv.org/abs/2302.07452}, \tpublisher = {arXiv}, \tjourn"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.7,
          "raw_context": "</tbody> </table>  \\*Evaluated on a subset of the wikipedia corpus that was available to us. All models use t"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bert",
          "confidence": 0.5,
          "raw_context": "model_type: bert"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "wikipedia",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "000a38de9d60e64d843f6a64c3577b56101c186d030a91da75d7c933d4b86dde"
    },
    {
      "model_id": "cerebras/Dragon-DocChat-Query-Encoder",
      "scanned_at": "2026-07-15T02:10:37.453015Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.6,
          "raw_context": "/tbody> </table>   \\*Evaluated on a subset of the wikipedia corpus that was available to us. All models use t"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ds Generalizable Dense Retrieval, \turl = {https://arxiv.org/abs/2302.07452}, \tpublisher = {arXiv}, \tjourn"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.7,
          "raw_context": "/tbody> </table>   \\*Evaluated on a subset of the wikipedia corpus that was available to us. All models use t"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bert",
          "confidence": 0.5,
          "raw_context": "model_type: bert"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "wikipedia",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "f9b76f8ca8fa6a88c942ecf2274ab31112c042f5892b240682a51c35363485eb"
    },
    {
      "model_id": "cerebras/GLM-4.5-Air-REAP-82B-A12B",
      "scanned_at": "2026-07-15T02:10:40.226936Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.5-Air",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.5-Air"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:zai-org/GLM-4.5-Air",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:zai-org/GLM-4.5-Air"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.5-Air",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.5-Air",
      "base_model_chain": [
        "zai-org/GLM-4.5-Air"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "57f2786774caaab2a31520f6ddf63ba713ccb69e317697784c1a5177b1890d0c"
    },
    {
      "model_id": "cerebras/GLM-4.5-Air-REAP-82B-A12B-FP8",
      "scanned_at": "2026-07-15T02:10:44.808770Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.5-Air-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.5-Air-FP8"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:zai-org/GLM-4.5-Air-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:zai-org/GLM-4.5-Air-FP8"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.5-Air-FP8",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.5-Air-FP8",
      "base_model_chain": [
        "zai-org/GLM-4.5-Air-FP8"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "ecf296a03309836adc24a65a00a5136e8363e1eebeca72c611a03898e8da98ad"
    },
    {
      "model_id": "cerebras/GLM-4.6-REAP-218B-A32B",
      "scanned_at": "2026-07-15T02:10:49.428585Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.6-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.6-FP8"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:zai-org/GLM-4.6-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:zai-org/GLM-4.6-FP8"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.6-FP8",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.6-FP8",
      "base_model_chain": [
        "zai-org/GLM-4.6-FP8"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "c186573ada8e522a129b5122a05442e9a5da2422816dac98517fcdda46b8eeca"
    },
    {
      "model_id": "cerebras/GLM-4.6-REAP-218B-A32B-FP8",
      "scanned_at": "2026-07-15T02:10:54.009375Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.6-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.6-FP8"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:zai-org/GLM-4.6-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:zai-org/GLM-4.6-FP8"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.6-FP8",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.6-FP8",
      "base_model_chain": [
        "zai-org/GLM-4.6-FP8"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "7cef02cd1c7afc30cc24fa48f5c607ca82e2c872c6da15637676921f10afdfa8"
    },
    {
      "model_id": "cerebras/GLM-4.6-REAP-252B-A32B",
      "scanned_at": "2026-07-15T02:10:56.762543Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.6",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.6"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:zai-org/GLM-4.6",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:zai-org/GLM-4.6"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.6",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.6",
      "base_model_chain": [
        "zai-org/GLM-4.6"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "baf522303ad9d79ef357c0af2b3452bd199634e18c4c9a2fb343b91ad75760fb"
    },
    {
      "model_id": "cerebras/GLM-4.6-REAP-252B-A32B-FP8",
      "scanned_at": "2026-07-15T02:11:01.338270Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.6-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.6-FP8"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:zai-org/GLM-4.6-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:zai-org/GLM-4.6-FP8"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.6-FP8",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.6-FP8",
      "base_model_chain": [
        "zai-org/GLM-4.6-FP8"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "26597ac614cbaeb8ee9907828fdf0cc36ef6b11d1c42cb8a8105ea20054f7347"
    },
    {
      "model_id": "cerebras/GLM-4.6-REAP-268B-A32B",
      "scanned_at": "2026-07-15T02:11:04.096779Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.6",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.6"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:zai-org/GLM-4.6",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:zai-org/GLM-4.6"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.6",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.6",
      "base_model_chain": [
        "zai-org/GLM-4.6"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "d2b1e29dd43dca04b252fcab1454f50d97423ef7d7b5f774c5262f6fbeb66c3f"
    },
    {
      "model_id": "cerebras/GLM-4.6-REAP-268B-A32B-FP8",
      "scanned_at": "2026-07-15T02:11:06.850353Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.6-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.6-FP8"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:zai-org/GLM-4.6-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:zai-org/GLM-4.6-FP8"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.6-FP8",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.6-FP8",
      "base_model_chain": [
        "zai-org/GLM-4.6-FP8"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "361ae662a97db03b51f79fb0945684c266ce0b35c71e89587a71341ad976a984"
    },
    {
      "model_id": "cerebras/GLM-4.7-Flash-REAP-23B-A3B",
      "scanned_at": "2026-07-15T02:11:09.609501Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.7-Flash",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.7-Flash"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:zai-org/GLM-4.7-Flash",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:zai-org/GLM-4.7-Flash"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe_lite",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe_lite"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.7-Flash",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "uv pip install sglang==0.3.2.dev9039+pr-17247.g90c446848 --extra-index-url https://sgl-project.github"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.7-Flash",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.7-Flash",
      "base_model_chain": [
        "zai-org/GLM-4.7-Flash"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.35000000000000003,
      "provenance_hash": "d62ed749ca1b67809fe92fb0a8b289d5fa9d38fc0ad4738ef7f34b6e1de9b966"
    },
    {
      "model_id": "cerebras/GLM-4.7-REAP-218B-A32B",
      "scanned_at": "2026-07-15T02:11:14.228769Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.7",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.7"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:zai-org/GLM-4.7",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:zai-org/GLM-4.7"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.7",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.7",
      "base_model_chain": [
        "zai-org/GLM-4.7"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "dfddcf1dfa8eca57d44f19c18386c78f2b92afa490658e7fb4fc4eda655ae6e5"
    },
    {
      "model_id": "cerebras/GLM-4.7-REAP-218B-A32B-FP8",
      "scanned_at": "2026-07-15T02:11:18.819325Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.7-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.7-FP8"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:zai-org/GLM-4.7-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:zai-org/GLM-4.7-FP8"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.7-FP8",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.7-FP8",
      "base_model_chain": [
        "zai-org/GLM-4.7-FP8"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "5eef8ebb89aef1ec6b92f2b37b2a4f4e3450e3c042f2702480a51cc28737fb0b"
    },
    {
      "model_id": "cerebras/GLM-4.7-REAP-268B-A32B",
      "scanned_at": "2026-07-15T02:11:23.405235Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.7",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.7"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:zai-org/GLM-4.7",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:zai-org/GLM-4.7"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.7",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.7",
      "base_model_chain": [
        "zai-org/GLM-4.7"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "898dc952044cd868547f5683f747a4bf72b9970dfb97071edccf32e28c20b72b"
    },
    {
      "model_id": "cerebras/GLM-4.7-REAP-268B-A32B-FP8",
      "scanned_at": "2026-07-15T02:11:26.170836Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "zai-org/GLM-4.7-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:zai-org/GLM-4.7-FP8"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:zai-org/GLM-4.7-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:zai-org/GLM-4.7-FP8"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "glm4_moe",
          "confidence": 0.5,
          "raw_context": "model_type: glm4_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:zai-org/GLM-4.7-FP8",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "get=\"_blank\">technical blog</a>, <a href=\"https://arxiv.org/abs/2508.06471\" target=\"_blank\">technical rep"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "zai-org/GLM-4.7-FP8",
      "base_model_chain": [
        "zai-org/GLM-4.7-FP8"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "9631fe5d31138e64af9639b85d897b8458702162e59c63a19d348561cb77d077"
    },
    {
      "model_id": "cerebras/Kimi-Linear-REAP-35B-A3B-Instruct",
      "scanned_at": "2026-07-15T02:11:28.934227Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "moonshotai/Kimi-Linear-48B-A3B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:moonshotai/Kimi-Linear-48B-A3B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:moonshotai/Kimi-Linear-48B-A3B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:moonshotai/Kimi-Linear-48B-A3B-Instruct"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "kimi_linear",
          "confidence": 0.5,
          "raw_context": "model_type: kimi_linear"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:moonshotai/Kimi-Linear-48B-A3B-Instruct",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "92\" style=\"margin: 0 8px;\">     <img src=\"figures/arxiv.png\" height=\"16\" width=\"16\" style=\"display: inlin"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "moonshotai/Kimi-Linear-48B-A3B-Instruct",
      "base_model_chain": [
        "moonshotai/Kimi-Linear-48B-A3B-Instruct"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.25,
      "provenance_hash": "0c7727b04acfc08238c32ceb53f23891f9fb2cbd6732577190bfada75dbd9f96"
    },
    {
      "model_id": "cerebras/Llama-3-CBHybridL-8B",
      "scanned_at": "2026-07-15T02:11:33.507813Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "cbllama",
          "confidence": 0.5,
          "raw_context": "model_type: cbllama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "ad6bf5638d60970ee8e8916544af251260e4c2b9ac54f06a64af3746ebf6904b"
    },
    {
      "model_id": "cerebras/Llama-3-CBHybridM-8B",
      "scanned_at": "2026-07-15T02:11:36.520379Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "cbllama",
          "confidence": 0.5,
          "raw_context": "model_type: cbllama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "59d3af586d9b144f4d7987ceaf4e31df6141c7555ea566b32de2980a01ab712e"
    },
    {
      "model_id": "cerebras/Llama3-DocChat-1.0-8B",
      "scanned_at": "2026-07-15T02:11:39.268354Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "openassistant",
          "confidence": 0.7,
          "raw_context": "Linguistics},\r   year={2023}\r }\r @article{kopf2024openassistant,\r   title={Openassistant conversations-democratiz"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "squad",
          "confidence": 0.7,
          "raw_context": "},\r   year={2019}\r }\r @inproceedings{rajpurkar2016squad,\r   title={SQuAD: 100,000+ Questions for Machine"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "eprint={2402.16671},\r       archivePrefix={arXiv},\r       primaryClass={cs.CL}\r }\r @article{llama3"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "openassistant",
        "squad",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.25,
      "provenance_hash": "fa06bae6b606349741f99a2d5670500fb0c3d6042ec41d3c612011c7329e25de"
    },
    {
      "model_id": "cerebras/MiniMax-M2-REAP-139B-A10B",
      "scanned_at": "2026-07-15T02:11:42.024982Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "MiniMaxAI/MiniMax-M2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:MiniMaxAI/MiniMax-M2"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:MiniMaxAI/MiniMax-M2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:MiniMaxAI/MiniMax-M2"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "minimax_m2",
          "confidence": 0.5,
          "raw_context": "model_type: minimax_m2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "29.7374C5.7791 29.7374 4 27.9583 4 25.7722V22.9878C4 22.3635 4.50609 21.8574 5.13043 21.8574C5.75478 2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "d:  We use the same scaffold as [R2E-Gym](https://arxiv.org/pdf/2504.07164) (Jain et al. 2025) on top of"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "MiniMaxAI/MiniMax-M2",
      "base_model_chain": [
        "MiniMaxAI/MiniMax-M2"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "83ef442b569a070367a5a522e53b1c245a7f02fcedcac27ad3cf4b8a05eb61b9"
    },
    {
      "model_id": "cerebras/MiniMax-M2-REAP-162B-A10B",
      "scanned_at": "2026-07-15T02:11:46.634478Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "MiniMaxAI/MiniMax-M2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:MiniMaxAI/MiniMax-M2"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:MiniMaxAI/MiniMax-M2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:MiniMaxAI/MiniMax-M2"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "minimax_m2",
          "confidence": 0.5,
          "raw_context": "model_type: minimax_m2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "29.7374C5.7791 29.7374 4 27.9583 4 25.7722V22.9878C4 22.3635 4.50609 21.8574 5.13043 21.8574C5.75478 2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "d:  We use the same scaffold as [R2E-Gym](https://arxiv.org/pdf/2504.07164) (Jain et al. 2025) on top of"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "MiniMaxAI/MiniMax-M2",
      "base_model_chain": [
        "MiniMaxAI/MiniMax-M2"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "6889e9281bd46ed63aea634f007660249bbf092baa920ec832e52b4270d7baee"
    },
    {
      "model_id": "cerebras/MiniMax-M2-REAP-172B-A10B",
      "scanned_at": "2026-07-15T02:11:49.421257Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "MiniMaxAI/MiniMax-M2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:MiniMaxAI/MiniMax-M2"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:MiniMaxAI/MiniMax-M2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:MiniMaxAI/MiniMax-M2"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "minimax_m2",
          "confidence": 0.5,
          "raw_context": "model_type: minimax_m2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "29.7374C5.7791 29.7374 4 27.9583 4 25.7722V22.9878C4 22.3635 4.50609 21.8574 5.13043 21.8574C5.75478 2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "d:  We use the same scaffold as [R2E-Gym](https://arxiv.org/pdf/2504.07164) (Jain et al. 2025) on top of"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "MiniMaxAI/MiniMax-M2",
      "base_model_chain": [
        "MiniMaxAI/MiniMax-M2"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "263b6bc3fdc7850076e392f67beac61e201aae4520dd6f3f774688edc6f457e5"
    },
    {
      "model_id": "cerebras/MiniMax-M2.1-REAP-139B-A10B",
      "scanned_at": "2026-07-15T02:11:52.181662Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "MiniMaxAI/MiniMax-M2.1",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:MiniMaxAI/MiniMax-M2.1"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:MiniMaxAI/MiniMax-M2.1",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:MiniMaxAI/MiniMax-M2.1"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "minimax_m2",
          "confidence": 0.5,
          "raw_context": "model_type: minimax_m2"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2.1",
          "value": "VIBE",
          "confidence": 0.48,
          "raw_context": "of 3 runs. We have open-sourced this benchmark at [VIBE](https://huggingface.co/datasets/MiniMaxAI/VIBE). > - **Toolathlon**: The evaluatio"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2.1",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "29.7374C5.7791 29.7374 4 27.9583 4 25.7722V22.9878C4 22.3635 4.50609 21.8574 5.13043 21.8574C5.75478 2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2.1",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "the same agent framework as [WebExplorer](https://arxiv.org/pdf/2509.06501) (Liu et al. 2025), with only"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "VIBE",
        "arxiv"
      ],
      "base_model": "MiniMaxAI/MiniMax-M2.1",
      "base_model_chain": [
        "MiniMaxAI/MiniMax-M2.1"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.35000000000000003,
      "provenance_hash": "627b35b8bced466a70ff132a3873f28e97de0a1508a60e149c4f82334281606c"
    },
    {
      "model_id": "cerebras/MiniMax-M2.1-REAP-172B-A10B",
      "scanned_at": "2026-07-15T02:11:56.768545Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "MiniMaxAI/MiniMax-M2.1",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:MiniMaxAI/MiniMax-M2.1"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:MiniMaxAI/MiniMax-M2.1",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:MiniMaxAI/MiniMax-M2.1"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "minimax_m2",
          "confidence": 0.5,
          "raw_context": "model_type: minimax_m2"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2.1",
          "value": "VIBE",
          "confidence": 0.48,
          "raw_context": "of 3 runs. We have open-sourced this benchmark at [VIBE](https://huggingface.co/datasets/MiniMaxAI/VIBE). > - **Toolathlon**: The evaluatio"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2.1",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "29.7374C5.7791 29.7374 4 27.9583 4 25.7722V22.9878C4 22.3635 4.50609 21.8574 5.13043 21.8574C5.75478 2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2.1",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "the same agent framework as [WebExplorer](https://arxiv.org/pdf/2509.06501) (Liu et al. 2025), with only"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "VIBE",
        "arxiv"
      ],
      "base_model": "MiniMaxAI/MiniMax-M2.1",
      "base_model_chain": [
        "MiniMaxAI/MiniMax-M2.1"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.35000000000000003,
      "provenance_hash": "5d4f93859f505f2da5fba02dcbd28c99d2cfb34327d752f80a6502f9cd623434"
    },
    {
      "model_id": "cerebras/MiniMax-M2.5-REAP-139B-A10B",
      "scanned_at": "2026-07-15T02:11:59.534265Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "MiniMaxAI/MiniMax-M2.5",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:MiniMaxAI/MiniMax-M2.5"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:MiniMaxAI/MiniMax-M2.5",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:MiniMaxAI/MiniMax-M2.5"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "details, refer to the following resources:  - [🧾 arXiv Preprint](https://arxiv.org/abs/2510.13999) - [🧾"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "minimax_m2",
          "confidence": 0.5,
          "raw_context": "model_type: minimax_m2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2.5",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "29.7374C5.7791 29.7374 4 27.9583 4 25.7722V22.9878C4 22.3635 4.50609 21.8574 5.13043 21.8574C5.75478 2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "MiniMaxAI/MiniMax-M2.5",
      "base_model_chain": [
        "MiniMaxAI/MiniMax-M2.5"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "3407a63050001e1b5d6c5b7cd9d0ca0849bfac9a2fd0f6ea2aefc3797b799e03"
    },
    {
      "model_id": "cerebras/MiniMax-M2.5-REAP-172B-A10B",
      "scanned_at": "2026-07-15T02:12:04.150159Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "MiniMaxAI/MiniMax-M2.5",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:MiniMaxAI/MiniMax-M2.5"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:MiniMaxAI/MiniMax-M2.5",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:MiniMaxAI/MiniMax-M2.5"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "details, refer to the following resources:  - [🧾 arXiv Preprint](https://arxiv.org/abs/2510.13999) - [🧾"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "minimax_m2",
          "confidence": 0.5,
          "raw_context": "model_type: minimax_m2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MiniMaxAI/MiniMax-M2.5",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "29.7374C5.7791 29.7374 4 27.9583 4 25.7722V22.9878C4 22.3635 4.50609 21.8574 5.13043 21.8574C5.75478 2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "MiniMaxAI/MiniMax-M2.5",
      "base_model_chain": [
        "MiniMaxAI/MiniMax-M2.5"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "ffd465de8536f81fbe743dd9bc7524f71fcec777f0eb0f945c4b5ca03231835d"
    },
    {
      "model_id": "cerebras/Qwen3-Coder-REAP-246B-A35B",
      "scanned_at": "2026-07-15T02:12:06.915046Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Qwen/Qwen3-Coder-480B-A35B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Qwen/Qwen3-Coder-480B-A35B-Instruct"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3_moe",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "base_model_chain": [
        "Qwen/Qwen3-Coder-480B-A35B-Instruct"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "f7fd61d9a1669d9b12245d6a6c41aa30eb5eaf45cd812a1e1504ccab24c45fd7"
    },
    {
      "model_id": "cerebras/Qwen3-Coder-REAP-246B-A35B-FP8",
      "scanned_at": "2026-07-15T02:12:11.512207Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "c datasets including:\r - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1))\r - Function ca"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "vol-codealpaca-v1))\r - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k))\r - Agentic"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "calling-60k))\r - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))\r \r 📚 For more d"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "including:\r - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).\r \r -"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3_moe",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
      "base_model_chain": [
        "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "67b1bbdaee238766b06e4988a752c4d987011778a5b2de1297ae6d027b0fd8b0"
    },
    {
      "model_id": "cerebras/Qwen3-Coder-REAP-25B-A3B",
      "scanned_at": "2026-07-15T02:12:16.135815Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Qwen/Qwen3-Coder-30B-A3B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Qwen/Qwen3-Coder-30B-A3B-Instruct"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3_moe",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
      "base_model_chain": [
        "Qwen/Qwen3-Coder-30B-A3B-Instruct"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "9723942261a92a30418bde4062f965d58f3de7abd95b963a40a30b8b82e1b5c1"
    },
    {
      "model_id": "cerebras/Qwen3-Coder-REAP-363B-A35B",
      "scanned_at": "2026-07-15T02:12:20.785662Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Qwen/Qwen3-Coder-480B-A35B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Qwen/Qwen3-Coder-480B-A35B-Instruct"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "ic datasets including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)) - Function cal"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "evol-codealpaca-v1)) - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)) - Agentic m"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "-calling-60k)) - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))  📚 For more det"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "s including: - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).  ---"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3_moe",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "base_model_chain": [
        "Qwen/Qwen3-Coder-480B-A35B-Instruct"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "d80934c061be106956da77ee897c0d668b246b509db97133238e616bf73646e4"
    },
    {
      "model_id": "cerebras/Qwen3-Coder-REAP-363B-A35B-FP8",
      "scanned_at": "2026-07-15T02:12:23.571580Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "evol-codealpaca",
          "confidence": 0.6,
          "raw_context": "c datasets including:\r - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1))\r - Function ca"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "xlam-function-calling",
          "confidence": 0.6,
          "raw_context": "vol-codealpaca-v1))\r - Function calling examples ([xlam-function-calling](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k))\r - Agentic"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SWE-smith-trajectories",
          "confidence": 0.6,
          "raw_context": "calling-60k))\r - Agentic multi-turn trajectories ([SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories))\r \r 📚 For more d"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "including:\r - Code generation samples ([evol-codealpaca](https://huggingface.co/datasets/theblackcat102/e"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tails on the evaluation setup, refer to the [REAP arXiv preprint](https://arxiv.org/abs/2510.13999).\r \r -"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3_moe",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3_moe"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "alpaca",
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
      "base_model_chain": [
        "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "50f908e4ca0ca18cef534bc6e06f949761468f532d476b872926db2e4069676a"
    },
    {
      "model_id": "cerebras/Step-3.5-Flash-REAP-121B-A11B",
      "scanned_at": "2026-07-15T02:12:26.324431Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "stepfun-ai/Step-3.5-Flash",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:stepfun-ai/Step-3.5-Flash"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:stepfun-ai/Step-3.5-Flash",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:stepfun-ai/Step-3.5-Flash"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "details, refer to the following resources:  - [🧾 arXiv Preprint](https://arxiv.org/abs/2510.13999) - [🧾"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "step3p5",
          "confidence": 0.5,
          "raw_context": "model_type: step3p5"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:stepfun-ai/Step-3.5-Flash",
          "value": "voc",
          "confidence": 0.5599999999999999,
          "raw_context": "6 hidden dim) | | **Context Window** | 256K | | **Vocabulary** | 128,896 tokens | | **Total Parameters*"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:stepfun-ai/Step-3.5-Flash",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ".5-flash/) [![Paper](https://img.shields.io/badge/Arxiv-TechReport-red)](https://arxiv.org/abs/2602.10604"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": "stepfun-ai/Step-3.5-Flash",
      "base_model_chain": [
        "stepfun-ai/Step-3.5-Flash",
        "stepfun-ai/step-3.5-flash"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "3df1b014d4903644a5e688f70e59f579961561cc4f84f2d50e65596c90c5b748"
    },
    {
      "model_id": "cerebras/Step-3.5-Flash-REAP-149B-A11B",
      "scanned_at": "2026-07-15T02:12:32.030110Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "stepfun-ai/Step-3.5-Flash",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:stepfun-ai/Step-3.5-Flash"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:stepfun-ai/Step-3.5-Flash",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:stepfun-ai/Step-3.5-Flash"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "details, refer to the following resources:  - [🧾 arXiv Preprint](https://arxiv.org/abs/2510.13999) - [🧾"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "step3p5",
          "confidence": 0.5,
          "raw_context": "model_type: step3p5"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:stepfun-ai/Step-3.5-Flash",
          "value": "voc",
          "confidence": 0.5599999999999999,
          "raw_context": "6 hidden dim) | | **Context Window** | 256K | | **Vocabulary** | 128,896 tokens | | **Total Parameters*"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:stepfun-ai/Step-3.5-Flash",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ".5-flash/) [![Paper](https://img.shields.io/badge/Arxiv-TechReport-red)](https://arxiv.org/abs/2602.10604"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": "stepfun-ai/Step-3.5-Flash",
      "base_model_chain": [
        "stepfun-ai/Step-3.5-Flash",
        "stepfun-ai/step-3.5-flash"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "5bd65f15732a3c54ca1d36b1cf0949dcbcb58fa92177bcf4f7956553259e2cf4"
    },
    {
      "model_id": "cerebras/btlm-3b-8k-base",
      "scanned_at": "2026-07-15T02:12:34.811110Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "cerebras/SlimPajama-627B",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:cerebras/SlimPajama-627B"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SlimPajama",
          "confidence": 0.6,
          "raw_context": "th an 8k context length trained on 627B tokens of [SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B). BTLM-3B-8k-base sets a"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "RedPajama",
          "confidence": 0.6,
          "raw_context": "harms:** There may be distributional bias in the [RedPajama dataset](https://huggingface.co/datasets/together"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "SlimPajama-627B - Tokenizer: Byte Pair Encoding - Vocabulary Size: 50257 - Sequence Length: 8192 - Opti"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "slimpajama",
          "confidence": 0.7,
          "raw_context": "causal-lm - Cerebras - BTLM datasets: - cerebras/SlimPajama-627B pipeline_tag: text-generation license: apach"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "h a similar architecture to [CerebrasGPT](https://arxiv.org/abs/2304.03208) with the addition of [SwiGLU]"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "redpajama",
          "confidence": 0.7,
          "raw_context": "harms:** There may be distributional bias in the [RedPajama dataset](https://huggingface.co/datasets/together"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "cerebras/btlm-3b-8k-base",
          "confidence": 0.9,
          "raw_context": "_name_or_path: cerebras/btlm-3b-8k-base"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "btlm",
          "confidence": 0.5,
          "raw_context": "model_type: btlm"
        }
      ],
      "declared_datasets": [
        "cerebras/SlimPajama-627B"
      ],
      "inferred_datasets": [
        "voc",
        "redpajama",
        "slimpajama",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.4,
      "provenance_hash": "e7e9c42fd21788e4c72e0bf07ad505a933013902531ab8ad691a6a0b000bef43"
    },
    {
      "model_id": "cerebras/btlm-3b-8k-chat",
      "scanned_at": "2026-07-15T02:12:37.578968Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "cerebras/SlimPajama-627B",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:cerebras/SlimPajama-627B"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "Anthropic/hh-rlhf",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:Anthropic/hh-rlhf"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "SlimPajama",
          "confidence": 0.6,
          "raw_context": "causal-lm - Cerebras - BTLM datasets: - cerebras/SlimPajama-627B - Anthropic/hh-rlhf pipeline_tag: text-gener"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "RedPajama",
          "confidence": 0.6,
          "raw_context": "harms:** There may be distributional bias in the [RedPajama dataset](https://huggingface.co/datasets/together"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "squad",
          "confidence": 0.7,
          "raw_context": "lling\", 2012 – Documentary about Indonesian death squad members who reenact scenes from classic Hollywood"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "slimpajama",
          "confidence": 0.7,
          "raw_context": "causal-lm - Cerebras - BTLM datasets: - cerebras/SlimPajama-627B - Anthropic/hh-rlhf pipeline_tag: text-gener"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "oscar",
          "confidence": 0.7,
          "raw_context": "e; it won numerous international prizes including Oscar nomination for Best Foreign Language Film (2012)."
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "tlm-3b-8k-base) model trained using [DPO](https://arxiv.org/abs/2305.18290) method on [Anthropic-HH-RLHF]"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "redpajama",
          "confidence": 0.7,
          "raw_context": "harms:** There may be distributional bias in the [RedPajama dataset](https://huggingface.co/datasets/together"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "cerebras/btlm-3b-8k-dpo",
          "confidence": 0.9,
          "raw_context": "_name_or_path: cerebras/btlm-3b-8k-dpo"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "btlm",
          "confidence": 0.5,
          "raw_context": "model_type: btlm"
        }
      ],
      "declared_datasets": [
        "cerebras/SlimPajama-627B",
        "Anthropic/hh-rlhf"
      ],
      "inferred_datasets": [
        "redpajama",
        "squad",
        "arxiv",
        "oscar",
        "slimpajama"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8,
      "provenance_hash": "ac0b99a6ae4bcab0a538b97486db8717dfdb4e7d2749b9b1c9b1ccacadeca664"
    },
    {
      "model_id": "ceselder/cot-oracle-ablation-pooling-stride100-3layers",
      "scanned_at": "2026-07-15T02:12:40.342011Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen3-8B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen3-8B"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-8B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-8B"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-8B",
          "confidence": 0.85,
          "raw_context": "--- base_model: Qwen/Qwen3-8B library_name: peft pipeline_tag: text-generation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).  - **Hardware Type:** [More"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "adapter:Qwen/Qwen3-8B",
      "base_model_chain": [
        "adapter:Qwen/Qwen3-8B"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.45,
      "provenance_hash": "f6da4d647e6e89ab651467ae2d605e7799630dd64b67ad163425e19b15ca7b6a"
    },
    {
      "model_id": "ceselder/cot-oracle-calibration-dpo",
      "scanned_at": "2026-07-15T02:12:45.032266Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "21344e3595e577ee97488bdbfcd7568a63ad8072d4f5ce7b22cea845ab491eb9"
    },
    {
      "model_id": "ceselder/cot-oracle-v15-6layers-stochastic",
      "scanned_at": "2026-07-15T02:12:47.868992Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen3-8B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen3-8B"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-8B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-8B"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-8B",
          "confidence": 0.85,
          "raw_context": "--- base_model: Qwen/Qwen3-8B library_name: peft pipeline_tag: text-generation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).  - **Hardware Type:** [More"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "adapter:Qwen/Qwen3-8B",
      "base_model_chain": [
        "adapter:Qwen/Qwen3-8B"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.45,
      "provenance_hash": "c50761b23a136c5acde15de7121eea21b75fded666aa5623294dc16367c213ec"
    },
    {
      "model_id": "chendelong/DirectSAM-1800px-0424",
      "scanned_at": "2026-07-15T02:12:50.619329Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "\"[**Subobject-level Image Tokenization**](https://arxiv.org/abs/2402.14327)\" by Delong Chen, Samuel Cahya"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "segformer",
          "confidence": 0.5,
          "raw_context": "model_type: segformer"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "e1f2b7e637963c80cfd10515cd790c79bff446dd2d7020131a2fc9b83cf3e8e3"
    },
    {
      "model_id": "chenshuguang/ppo-Huggy",
      "scanned_at": "2026-07-15T02:12:53.363969Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "ebddc63f72c14c38856179942f6245a28b3abddd7fe91bd54f87daf958afa451"
    },
    {
      "model_id": "chenxie95/xlance-msr-ckpt",
      "scanned_at": "2026-07-15T02:12:56.125797Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.1,
      "provenance_hash": "272ec0ba396fda3698d79e97b4ade9063666c7d4a722d65bed9065306170b53f"
    },
    {
      "model_id": "cheposed/eennnddd132",
      "scanned_at": "2026-07-15T02:12:58.907041Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "9037b9cf604e0899a2e7b83b1b1229f9c057cc783768bc8cde9b036e092b7e52"
    },
    {
      "model_id": "chipcraftx-io/chipcraftx-rtlgen-7b",
      "scanned_at": "2026-07-15T02:13:01.674053Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen2.5-Coder-7B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen2.5-Coder-7B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Qwen/Qwen2.5-Coder-7B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Qwen/Qwen2.5-Coder-7B-Instruct"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen2.5-Coder-7B-Instruct",
          "confidence": 0.85,
          "raw_context": "ware-design - eda - code-generation - chip-design base_model: Qwen/Qwen2.5-Coder-7B-Instruct pipeline_tag: text-generation model-index: - name"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen2",
          "confidence": 0.5,
          "raw_context": "model_type: qwen2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen2.5-Coder-7B-Instruct",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "tation](https://qwen.readthedocs.io/en/latest/), [Arxiv](https://arxiv.org/abs/2409.12186).  ## Requireme"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen2.5-Coder-7B-Instruct",
      "base_model_chain": [
        "Qwen/Qwen2.5-Coder-7B-Instruct",
        "Qwen/Qwen2.5-Coder-7B",
        "Qwen/Qwen2.5-7B"
      ],
      "training_section_present": true,
      "license": "cc-by-nc-4.0",
      "provenance_score": 0.55,
      "provenance_hash": "26b44efabc8183a4e4b531110561e770ce8e85c965c495e1110c8c473ef5acaf"
    },
    {
      "model_id": "chipcraftx-io/chipcraftx-rtlgen-7b-GGUF",
      "scanned_at": "2026-07-15T02:13:08.082980Z",
      "signals": [
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "ChipCraftX/chipcraftx-rtlgen-7b",
          "confidence": 0.85,
          "raw_context": "eration - chip-design - gguf - ollama - llama-cpp base_model: ChipCraftX/chipcraftx-rtlgen-7b pipeline_tag: text-generation ---  # chipcraftx-r"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "ChipCraftX/chipcraftx-rtlgen-7b",
      "base_model_chain": [
        "ChipCraftX/chipcraftx-rtlgen-7b"
      ],
      "training_section_present": false,
      "license": "cc-by-nc-4.0",
      "provenance_score": 0.2,
      "provenance_hash": "f0ffa9d9ff6841d6ac60031ea20595693984069be21c5d4ca882a3f26d4de62f"
    },
    {
      "model_id": "chrisjay/afrospeech-wav2vec-all-6",
      "scanned_at": "2026-07-15T02:13:12.680485Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "crowd-speech-africa",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:crowd-speech-africa"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "crowd-speech-africa",
          "confidence": 0.6,
          "raw_context": "s://huggingface.co/facebook/wav2vec2-base) on the [crowd-speech-africa](https://huggingface.co/datasets/chrisjay/crowd-speech-africa), which was a crowd-s"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "facebook/wav2vec2-base",
          "confidence": 0.9,
          "raw_context": "_name_or_path: facebook/wav2vec2-base"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "wav2vec2",
          "confidence": 0.5,
          "raw_context": "model_type: wav2vec2"
        }
      ],
      "declared_datasets": [
        "crowd-speech-africa"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.5,
      "provenance_hash": "e039e2fa53f62137ed1d2f3f0ce4dc61cd8f587fffd9f6215b4dd119c34e3546"
    },
    {
      "model_id": "chuhac/BiomedCLIP-vit-bert-hf",
      "scanned_at": "2026-07-15T02:13:15.433158Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "pubmed",
          "confidence": 0.7,
          "raw_context": "plementation of the original microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224 2. rename the checkp"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "clip",
          "confidence": 0.5,
          "raw_context": "model_type: clip"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "pubmed"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "9f38ceeebb9b6ca812f431c5a4cb758fb38ddf60ce88a28cad0655ea9b978ba2"
    },
    {
      "model_id": "chuongtonglong/cMZtIt6arizWhFv",
      "scanned_at": "2026-07-15T02:13:18.178753Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "848869282cdb4e3aee599d9e29ef56b166957fd20a209cdd606f690fe0bed9d2"
    },
    {
      "model_id": "chuongtonglong/iSNf0ydh5TWLxaJ",
      "scanned_at": "2026-07-15T02:13:20.921527Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "73e50846057990fe9f36f336ae8eabd4f4a79f3d630513d77d0ec795d0f18c70"
    },
    {
      "model_id": "chuongtonglong/xJPiun39xReCYuF",
      "scanned_at": "2026-07-15T02:13:23.653949Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "802440ea2e197292c8acdb22b5078079790085c0068ef39b67611155948a2b18"
    },
    {
      "model_id": "cindermond/world-model-plancraft-llama3-2-1b-instruct-filtered",
      "scanned_at": "2026-07-15T02:13:26.385744Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:meta-llama/Llama-3.2-1B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:meta-llama/Llama-3.2-1B-Instruct"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.85,
          "raw_context": "--- language: en library_name: peft base_model: meta-llama/Llama-3.2-1B-Instruct tags:   - world-model   - nesys   - lora ---  ##"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.85,
          "raw_context": "usalLM, AutoTokenizer from peft import PeftModel  base_model = \"meta-llama/Llama-3.2-1B-Instruct\" adapter_id = \"cindermond/world-model-plancraft-l"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "bolic Synergy for Interactive World Modeling”** ([arXiv:2602.10480](https://arxiv.org/abs/2602.10480))."
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "meta-llama/Llama-3.2-1B-Instruct",
      "base_model_chain": [
        "meta-llama/Llama-3.2-1B-Instruct"
      ],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "ff21faa09e2bfa01a3321933e01318323b96dc69b7cd391e9bfd928382cc3851"
    },
    {
      "model_id": "cindermond/world-model-plancraft-qwen3-4b-filtered",
      "scanned_at": "2026-07-15T02:13:30.967938Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-4B"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen3-4B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen3-4B"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.85,
          "raw_context": "--- language: en library_name: peft base_model: Qwen/Qwen3-4B tags:   - world-model   - nesys   - lora ---  ##"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.85,
          "raw_context": "usalLM, AutoTokenizer from peft import PeftModel  base_model = \"Qwen/Qwen3-4B\" adapter_id = \"cindermond/world-model-plancraft-q"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "bolic Synergy for Interactive World Modeling”** ([arXiv:2602.10480](https://arxiv.org/abs/2602.10480))."
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-4B",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "of up to 131,072 tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method.  YaRN is currently su"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-4B",
      "base_model_chain": [
        "Qwen/Qwen3-4B",
        "Qwen/Qwen3-4B-Base"
      ],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "6cc8abba297d930860405c8588268b61d373b65b4731c53d27da83fb242cd3be"
    },
    {
      "model_id": "cindermond/world-model-scienceworld-llama3-2-1b-instruct-filtered",
      "scanned_at": "2026-07-15T02:13:36.475556Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:meta-llama/Llama-3.2-1B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:meta-llama/Llama-3.2-1B-Instruct"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.85,
          "raw_context": "--- language: en library_name: peft base_model: meta-llama/Llama-3.2-1B-Instruct tags:   - world-model   - nesys   - lora ---  ##"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.85,
          "raw_context": "usalLM, AutoTokenizer from peft import PeftModel  base_model = \"meta-llama/Llama-3.2-1B-Instruct\" adapter_id = \"cindermond/world-model-scienceworl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "bolic Synergy for Interactive World Modeling”** ([arXiv:2602.10480](https://arxiv.org/abs/2602.10480))."
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "meta-llama/Llama-3.2-1B-Instruct",
      "base_model_chain": [
        "meta-llama/Llama-3.2-1B-Instruct"
      ],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "ebccf1e863090f95ea8e635db6905706f49c65f99568ae88603496dde1650d65"
    },
    {
      "model_id": "cindermond/world-model-scienceworld-qwen3-4b-filtered",
      "scanned_at": "2026-07-15T02:13:39.230380Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-4B"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen3-4B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen3-4B"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.85,
          "raw_context": "--- language: en library_name: peft base_model: Qwen/Qwen3-4B tags:   - world-model   - nesys   - lora ---  ##"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.85,
          "raw_context": "usalLM, AutoTokenizer from peft import PeftModel  base_model = \"Qwen/Qwen3-4B\" adapter_id = \"cindermond/world-model-scienceworl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "bolic Synergy for Interactive World Modeling”** ([arXiv:2602.10480](https://arxiv.org/abs/2602.10480))."
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-4B",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "of up to 131,072 tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method.  YaRN is currently su"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-4B",
      "base_model_chain": [
        "Qwen/Qwen3-4B",
        "Qwen/Qwen3-4B-Base"
      ],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "e5ac5f45266534efcb0d79c9ff3a195c71e37997cb8bc327295cef7c5b4f4b42"
    },
    {
      "model_id": "cindermond/world-model-webshop-llama3-2-1b-instruct-filtered",
      "scanned_at": "2026-07-15T02:13:41.985262Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:meta-llama/Llama-3.2-1B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:meta-llama/Llama-3.2-1B-Instruct"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.85,
          "raw_context": "--- language: en library_name: peft base_model: meta-llama/Llama-3.2-1B-Instruct tags:   - world-model   - nesys   - lora ---  ##"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "meta-llama/Llama-3.2-1B-Instruct",
          "confidence": 0.85,
          "raw_context": "usalLM, AutoTokenizer from peft import PeftModel  base_model = \"meta-llama/Llama-3.2-1B-Instruct\" adapter_id = \"cindermond/world-model-webshop-lla"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "bolic Synergy for Interactive World Modeling”** ([arXiv:2602.10480](https://arxiv.org/abs/2602.10480))."
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "meta-llama/Llama-3.2-1B-Instruct",
      "base_model_chain": [
        "meta-llama/Llama-3.2-1B-Instruct"
      ],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "7cb63bbcbfeb08db741cc488ac7a4896f379fda336215b41a606dfcdaa69b863"
    },
    {
      "model_id": "cindermond/world-model-webshop-qwen3-4b-filtered",
      "scanned_at": "2026-07-15T02:13:44.751879Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-4B"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen3-4B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen3-4B"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.85,
          "raw_context": "--- language: en library_name: peft base_model: Qwen/Qwen3-4B tags:   - world-model   - nesys   - lora ---  ##"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.85,
          "raw_context": "usalLM, AutoTokenizer from peft import PeftModel  base_model = \"Qwen/Qwen3-4B\" adapter_id = \"cindermond/world-model-webshop-qwe"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "bolic Synergy for Interactive World Modeling”** ([arXiv:2602.10480](https://arxiv.org/abs/2602.10480))."
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-4B",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "of up to 131,072 tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method.  YaRN is currently su"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-4B",
      "base_model_chain": [
        "Qwen/Qwen3-4B",
        "Qwen/Qwen3-4B-Base"
      ],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "02af55aec70f0c0f46689335aa3d7277f5f6490185a46e9c4138243d68738408"
    },
    {
      "model_id": "city96/FLUX.1-dev-gguf",
      "scanned_at": "2026-07-15T02:13:47.658250Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "black-forest-labs/FLUX.1-dev",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:black-forest-labs/FLUX.1-dev"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:black-forest-labs/FLUX.1-dev",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:black-forest-labs/FLUX.1-dev"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "black-forest-labs/FLUX.1-dev",
          "confidence": 0.85,
          "raw_context": "--- base_model: black-forest-labs/FLUX.1-dev library_name: gguf license: other license_name: f"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "black-forest-labs/FLUX.1-dev",
      "base_model_chain": [
        "black-forest-labs/FLUX.1-dev"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "2ca6e9b40cb692861e0328a8c9044717643e12679ec3dab48bd7259a7ba682c4"
    },
    {
      "model_id": "city96/FLUX.1-schnell-gguf",
      "scanned_at": "2026-07-15T02:13:52.224674Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "black-forest-labs/FLUX.1-schnell",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:black-forest-labs/FLUX.1-schnell"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:black-forest-labs/FLUX.1-schnell",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:black-forest-labs/FLUX.1-schnell"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "black-forest-labs/FLUX.1-schnell",
          "confidence": 0.85,
          "raw_context": "--- base_model: black-forest-labs/FLUX.1-schnell library_name: gguf license: apache-2.0 quantized_"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "black-forest-labs/FLUX.1-schnell",
      "base_model_chain": [
        "black-forest-labs/FLUX.1-schnell"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "0c08ea7c793336ebbb1b85568886f370f241ddc80bb962bfe7003244174a1d89"
    },
    {
      "model_id": "city96/FLUX.2-dev-gguf",
      "scanned_at": "2026-07-15T02:13:56.804694Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "black-forest-labs/FLUX.2-dev",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:black-forest-labs/FLUX.2-dev"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:black-forest-labs/FLUX.2-dev",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:black-forest-labs/FLUX.2-dev"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "black-forest-labs/FLUX.2-dev",
          "confidence": 0.85,
          "raw_context": "--- base_model: black-forest-labs/FLUX.2-dev library_name: gguf quantized_by: city96 license:"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "black-forest-labs/FLUX.2-dev",
      "base_model_chain": [
        "black-forest-labs/FLUX.2-dev"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "247fb707dfe264ab6d8176ec3b2f9b44015977e8385e2387529c4dd32368ec77"
    },
    {
      "model_id": "ckanu13kf/test",
      "scanned_at": "2026-07-15T02:14:01.489702Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "microsoft/layoutlmv2-base-uncased",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:microsoft/layoutlmv2-base-uncased"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:microsoft/layoutlmv2-base-uncased",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:microsoft/layoutlmv2-base-uncased"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "microsoft/layoutlmv2-base-uncased",
          "confidence": 0.85,
          "raw_context": "---\r license: cc-by-nc-sa-4.0\r base_model: microsoft/layoutlmv2-base-uncased\r tags:\r - generated_from_trainer\r model-index:\r -"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/layoutlmv2-base-uncased",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/layoutlmv2-base-uncased"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "layoutlmv2",
          "confidence": 0.5,
          "raw_context": "model_type: layoutlmv2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/layoutlmv2-base-uncased",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "for Visually-Rich Document Understanding](https://arxiv.org/abs/2012.14740) Yang Xu, Yiheng Xu, Tengchao"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "microsoft/layoutlmv2-base-uncased",
      "base_model_chain": [
        "microsoft/layoutlmv2-base-uncased"
      ],
      "training_section_present": true,
      "license": "cc-by-nc-sa-4.0",
      "provenance_score": 0.55,
      "provenance_hash": "284b1a624c5c9fc90848fb85ec774fd9471d9b5320ea92a1cdf483be7bc9be3e"
    },
    {
      "model_id": "cl-nagoya/ruri-v3-30m",
      "scanned_at": "2026-07-15T02:14:04.237156Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "cl-nagoya/ruri-v3-dataset-ft",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:cl-nagoya/ruri-v3-dataset-ft"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "cl-nagoya/ruri-v3-pt-30m",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:cl-nagoya/ruri-v3-pt-30m"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:cl-nagoya/ruri-v3-pt-30m",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:cl-nagoya/ruri-v3-pt-30m"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "cl-nagoya/ruri-v3-pt-30m",
          "confidence": 0.85,
          "raw_context": "tags: - sentence-similarity - feature-extraction base_model: cl-nagoya/ruri-v3-pt-30m widget: [] pipeline_tag: sentence-similarity lice"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "f Ruri (v1, v2) were limited to 512. - **Expanded vocabulary of 100K tokens**, compared to 32K in v1 an"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "se - **License:** Apache 2.0 - **Paper:** https://arxiv.org/abs/2409.07737   ### Full Model Architecture"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "outputs/ft/vanilla/cl-nagoya__ruri-v3-pt-30m/B512E1LR1e-05L8192Temp0.01/default14",
          "confidence": 0.9,
          "raw_context": "_name_or_path: outputs/ft/vanilla/cl-nagoya__ruri-v3-pt-30m/B512E1LR1e-05L8192Temp0.01/default14"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "modernbert",
          "confidence": 0.5,
          "raw_context": "model_type: modernbert"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:cl-nagoya/ruri-v3-pt-30m",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "r={2024},   eprint={2409.07737},   archivePrefix={arXiv},   primaryClass={cs.CL},   url={https://arxiv.or"
        }
      ],
      "declared_datasets": [
        "cl-nagoya/ruri-v3-dataset-ft"
      ],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": "cl-nagoya/ruri-v3-pt-30m",
      "base_model_chain": [
        "cl-nagoya/ruri-v3-pt-30m",
        "sbintuitions/modernbert-ja-30m"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.4,
      "provenance_hash": "082c6478d061ee4f8327be1a1f7ad4ce1241dd52150c8cc9090966821c0f5049"
    },
    {
      "model_id": "classla/wav2vec2-xls-r-parlaspeech-hr",
      "scanned_at": "2026-07-15T02:14:09.762148Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "parlaspeech-hr",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:parlaspeech-hr"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "facebook/wav2vec2-xls-r-300m",
          "confidence": 0.9,
          "raw_context": "_name_or_path: facebook/wav2vec2-xls-r-300m"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "wav2vec2",
          "confidence": 0.5,
          "raw_context": "model_type: wav2vec2"
        }
      ],
      "declared_datasets": [
        "parlaspeech-hr"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.4,
      "provenance_hash": "112c7d092ccc586ad4d0ca39007d9fadcb72a255889ecca879c67e194a883e5e"
    },
    {
      "model_id": "cledoux42/Ethnicity_Test_v003",
      "scanned_at": "2026-07-15T02:14:12.568079Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "cledoux42/autotrain-data-ethnicity-test_v003",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:cledoux42/autotrain-data-ethnicity-test_v003"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "vit",
          "confidence": 0.5,
          "raw_context": "model_type: vit"
        }
      ],
      "declared_datasets": [
        "cledoux42/autotrain-data-ethnicity-test_v003"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.1,
      "provenance_hash": "9c3ad981fd08df373a02e4450d2b513c577f05e57df9828c59dabc81ac557301"
    },
    {
      "model_id": "cli08/qwen3-0.6-finetuned",
      "scanned_at": "2026-07-15T02:14:15.326293Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen3-0.6B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen3-0.6B"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "sh0416/ag_news",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:sh0416/ag_news"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-0.6B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-0.6B"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "sh0416/ag_news",
          "confidence": 0.8,
          "raw_context": "B](https://huggingface.co/Qwen/Qwen3-0.6B) on the [sh0416/ag_news](https://huggingface.co/datasets/sh0416/ag_news) dataset. It achieved an F1 of 0.91"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-0.6B",
          "confidence": 0.85,
          "raw_context": "--- library_name: peft license: apache-2.0 base_model: Qwen/Qwen3-0.6B tags: - base_model:adapter:Qwen/Qwen3-0.6B - lora"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [
        "sh0416/ag_news"
      ],
      "inferred_datasets": [],
      "base_model": "adapter:Qwen/Qwen3-0.6B",
      "base_model_chain": [
        "adapter:Qwen/Qwen3-0.6B"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.6,
      "provenance_hash": "ebfcddaaaf7931d492f7705ea1b4c42d046a3da533181fa9dc7183208234cfa8"
    },
    {
      "model_id": "cliffer1/videomae-base-finetuned-kinetics-violence-nonviolence-tuned",
      "scanned_at": "2026-07-15T02:14:19.947703Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "MCG-NJU/videomae-base-finetuned-kinetics",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:MCG-NJU/videomae-base-finetuned-kinetics"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:MCG-NJU/videomae-base-finetuned-kinetics",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:MCG-NJU/videomae-base-finetuned-kinetics"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "MCG-NJU/videomae-base-finetuned-kinetics",
          "confidence": 0.85,
          "raw_context": "library_name: transformers license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base-finetuned-kinetics tags: - generated_from_trainer metrics: - accurac"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "MCG-NJU/videomae-base-finetuned-kinetics",
          "confidence": 0.9,
          "raw_context": "_name_or_path: MCG-NJU/videomae-base-finetuned-kinetics"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "videomae",
          "confidence": 0.5,
          "raw_context": "model_type: videomae"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:MCG-NJU/videomae-base-finetuned-kinetics",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "s for Self-Supervised Video Pre-Training](https://arxiv.org/abs/2203.12602) by Tong et al. and first rele"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "MCG-NJU/videomae-base-finetuned-kinetics",
      "base_model_chain": [
        "MCG-NJU/videomae-base-finetuned-kinetics"
      ],
      "training_section_present": true,
      "license": "cc-by-nc-4.0",
      "provenance_score": 0.55,
      "provenance_hash": "abd49b652a7ecac4e161b76dcd90b9510308ba2909b764024f180b9947ce2e4c"
    },
    {
      "model_id": "cmarkea/bloomz-560m-nli",
      "scanned_at": "2026-07-15T02:14:24.606289Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "xnli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:xnli"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "cmarkea/bloomz-560m-nli",
          "confidence": 0.9,
          "raw_context": "_name_or_path: cmarkea/bloomz-560m-nli"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "xnli"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.2,
      "provenance_hash": "62c4d8d3b93210216ab1d48d9983c699bebc9979496de62d348d9486bf9af34c"
    },
    {
      "model_id": "cmarkea/bloomz-7b1-mt-nli",
      "scanned_at": "2026-07-15T02:14:27.377786Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "xnli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:xnli"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "cmarkea/bloomz-7b1-mt-dpo-chat",
          "confidence": 0.9,
          "raw_context": "_name_or_path: cmarkea/bloomz-7b1-mt-dpo-chat"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bloom",
          "confidence": 0.5,
          "raw_context": "model_type: bloom"
        }
      ],
      "declared_datasets": [
        "xnli"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "bigscience-bloom-rail-1.0",
      "provenance_score": 0.2,
      "provenance_hash": "f45eae0869d2b240683fe0ef1436c97446a1c4b0676ee38831742617de13275e"
    },
    {
      "model_id": "cmarkea/detr-layout-detection",
      "scanned_at": "2026-07-15T02:14:30.133500Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ds4sd/DocLayNet",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ds4sd/DocLayNet"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "DocLayNet",
          "confidence": 0.6,
          "raw_context": "://huggingface.co/facebook/detr-resnet-50) on the [DocLayNet](https://huggingface.co/datasets/ds4sd/DocLayNet) dataset. This model can jointly p"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "cmarkea/detr-layout-detection",
          "confidence": 0.9,
          "raw_context": "_name_or_path: cmarkea/detr-layout-detection"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "detr",
          "confidence": 0.5,
          "raw_context": "model_type: detr"
        }
      ],
      "declared_datasets": [
        "ds4sd/DocLayNet"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "a3d0fdfef273111106fee12f5bd22b7148b8120b498ee912b5ae636ba934f874"
    },
    {
      "model_id": "cmarkea/distilcamembert-base-nli",
      "scanned_at": "2026-07-15T02:14:32.912335Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "flue",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:flue"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "cmarkea/distilcamembert-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:cmarkea/distilcamembert-base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:cmarkea/distilcamembert-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:cmarkea/distilcamembert-base"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "FLUE",
          "confidence": 0.6,
          "raw_context": "amemBERT.  Dataset -------  The dataset XNLI from [FLUE](https://huggingface.co/datasets/flue) comprises 392,702 premises with their hypoth"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "allocine",
          "confidence": 0.6,
          "raw_context": "or this part, we use two datasets, the first one: [allocine](https://huggingface.co/datasets/allocine) used to train the sentiment analysis mod"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "mlsum",
          "confidence": 0.6,
          "raw_context": "84.97         | 70.05         |  The second one: [mlsum](https://huggingface.co/datasets/mlsum) used to train the summarization models. In"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.6,
          "raw_context": "CC (Matthews Correlation Coefficient)](https://en.wikipedia.org/wiki/Phi_coefficient) were used. We used an *"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.7,
          "raw_context": "CC (Matthews Correlation Coefficient)](https://en.wikipedia.org/wiki/Phi_coefficient) were used. We used an *"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "cmarkea/distilcamembert-base-nli",
          "confidence": 0.9,
          "raw_context": "_name_or_path: cmarkea/distilcamembert-base-nli"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "camembert",
          "confidence": 0.5,
          "raw_context": "model_type: camembert"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:cmarkea/distilcamembert-base",
          "value": "FLUE",
          "confidence": 0.48,
          "raw_context": "t name | f1-score | | :----------: | :------: | | [FLUE](https://huggingface.co/datasets/flue) CLS     | 83%      | | [FLUE](https://huggin"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:cmarkea/distilcamembert-base",
          "value": "wikiner_fr",
          "confidence": 0.48,
          "raw_context": "gingface.co/datasets/flue) XNLI    | 77%      | | [wikiner_fr](https://huggingface.co/datasets/Jean-Baptiste/wikiner_fr) NER | 98%    |  How to u"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:cmarkea/distilcamembert-base",
          "value": "oscar",
          "confidence": 0.5599999999999999,
          "raw_context": "--- language: fr license: mit datasets: - oscar widget: - text: \"J'aime lire les <mask> de SF.\" -"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:cmarkea/distilcamembert-base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "oncept is shown in the [DistilBERT paper](https://arxiv.org/abs/1910.01108) and the code used for the tra"
        }
      ],
      "declared_datasets": [
        "flue"
      ],
      "inferred_datasets": [
        "wikipedia",
        "arxiv",
        "oscar",
        "wikiner_fr",
        "FLUE"
      ],
      "base_model": "cmarkea/distilcamembert-base",
      "base_model_chain": [
        "cmarkea/distilcamembert-base"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.5,
      "provenance_hash": "7391a5d53c4449cf445b17132d1e3e2a4e52965d322dac6bd5778a5c48e0e119"
    },
    {
      "model_id": "cocktailpeanut/oa",
      "scanned_at": "2026-07-15T02:14:37.586620Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "dual_ar",
          "confidence": 0.5,
          "raw_context": "model_type: dual_ar"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "cc-by-nc-sa-4.0",
      "provenance_score": 0.1,
      "provenance_hash": "ff1ec0ff087d603913b47a0813330d13294fc8f089b1f200670d12244a4cb377"
    },
    {
      "model_id": "cocktailpeanut/rm",
      "scanned_at": "2026-07-15T02:14:40.337072Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "ZhengPeng7/BiRefNet",
          "confidence": 0.9,
          "raw_context": "_name_or_path: ZhengPeng7/BiRefNet"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "other",
      "provenance_score": 0.4,
      "provenance_hash": "ab51bfa89f45a5dcec890979c21d1db9040750ce1c0a47b867918d232de3a290"
    },
    {
      "model_id": "codeconflict7/joblib-mmap-bypass-poc",
      "scanned_at": "2026-07-15T02:14:43.140821Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "2e4c132bd36d2095089a95244bb3d89c94293040549d232c557a4af253a914ab"
    },
    {
      "model_id": "codefuse-ai/F2LLM-v2-4B-Preview",
      "scanned_at": "2026-07-15T02:14:45.897595Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "codefuse-ai/F2LLM-v2",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:codefuse-ai/F2LLM-v2"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-4B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-4B"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Qwen/Qwen3-4B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Qwen/Qwen3-4B"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": ",       eprint={2603.19223},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-4B",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "of up to 131,072 tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method.  YaRN is currently su"
        }
      ],
      "declared_datasets": [
        "codefuse-ai/F2LLM-v2"
      ],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-4B",
      "base_model_chain": [
        "Qwen/Qwen3-4B",
        "Qwen/Qwen3-4B-Base"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.35000000000000003,
      "provenance_hash": "301ac671b42a35ce0f0b413cf3f558c7ea55c85d3e59134fe4cebf0532a26143"
    },
    {
      "model_id": "cognitivecomputations/dolphin-2.6-mixtral-8x7b",
      "scanned_at": "2026-07-15T02:14:48.657161Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ehartford/dolphin",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ehartford/dolphin"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "jondurbin/airoboros-2.2.1",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:jondurbin/airoboros-2.2.1"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ehartford/dolphin-coder",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ehartford/dolphin-coder"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "teknium/openhermes",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:teknium/openhermes"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ise-uiuc/Magicoder-OSS-Instruct-75K",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ise-uiuc/Magicoder-OSS-Instruct-75K"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ise-uiuc/Magicoder-Evol-Instruct-110K",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ise-uiuc/Magicoder-Evol-Instruct-110K"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "LDJnr/Capybara",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:LDJnr/Capybara"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/workspace/models/Mixtral-8x7B-v0.1",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /workspace/models/Mixtral-8x7B-v0.1"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "mixtral",
          "confidence": 0.5,
          "raw_context": "model_type: mixtral"
        }
      ],
      "declared_datasets": [
        "ehartford/dolphin-coder",
        "ise-uiuc/Magicoder-Evol-Instruct-110K",
        "teknium/openhermes",
        "ise-uiuc/Magicoder-OSS-Instruct-75K",
        "ehartford/dolphin",
        "LDJnr/Capybara",
        "jondurbin/airoboros-2.2.1"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.7,
      "provenance_hash": "2df835e21dbb81df643660a055dd30f9def823fbd6fd4474f4f87caa402f14f8"
    },
    {
      "model_id": "cointegrated/rubert-base-cased-nli-twoway",
      "scanned_at": "2026-07-15T02:14:51.744122Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "cointegrated/nli-rus-translated-v2021",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:cointegrated/nli-rus-translated-v2021"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/gd/MyDrive/models/rubert-base-cased-nli-twoway",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /gd/MyDrive/models/rubert-base-cased-nli-twoway"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bert",
          "confidence": 0.5,
          "raw_context": "model_type: bert"
        }
      ],
      "declared_datasets": [
        "cointegrated/nli-rus-translated-v2021"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.1,
      "provenance_hash": "d28094c66286483e30e9986c56e009298f130ee5ceab72e053fbc57d069be310"
    },
    {
      "model_id": "cointegrated/rubert-tiny-bilingual-nli",
      "scanned_at": "2026-07-15T02:14:54.494575Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "cointegrated/nli-rus-translated-v2021",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:cointegrated/nli-rus-translated-v2021"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/gd/MyDrive/models/rubert-tiny-nli-twoway",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /gd/MyDrive/models/rubert-tiny-nli-twoway"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bert",
          "confidence": 0.5,
          "raw_context": "model_type: bert"
        }
      ],
      "declared_datasets": [
        "cointegrated/nli-rus-translated-v2021"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.1,
      "provenance_hash": "7961783778c4fce24d36d2d91e620f3efc3379544c6546f13f67233c3fc62ceb"
    },
    {
      "model_id": "conghuudanh35/7pqbFJEWaezoDDJ",
      "scanned_at": "2026-07-15T02:14:57.237882Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "f9f0fcbbcf287fec8f9d6ccc9c5d7643476ef69c3a0afe654755a005bc27844c"
    },
    {
      "model_id": "conghuudanh35/Bfdt9sclphhIrKx",
      "scanned_at": "2026-07-15T02:14:59.975293Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "6c1d42fd04344094df19c299116dc332d4e868a5372c6f6ad39859556823ba72"
    },
    {
      "model_id": "conghuudanh35/D6ok8yMgDhizEnn",
      "scanned_at": "2026-07-15T02:15:02.708725Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "bf16ccc77cd8b392fc29508ac9d743f5638e69477c230540035ee0ca17915679"
    },
    {
      "model_id": "congthiha83/eVfcMwtwiA6RHCX",
      "scanned_at": "2026-07-15T02:15:05.465826Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "e8643cac0047f095f3129c5f2adf211df6828b14e82da001ab73d8c145e0bc69"
    },
    {
      "model_id": "congthiha83/jfW4cDRGF8EaBDu",
      "scanned_at": "2026-07-15T02:15:08.285656Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "28e67d4a1d0347bacbb7eeb7b75bd5a96d1ef7358b858b56d81eb2fe72807d76"
    },
    {
      "model_id": "congthiha83/kLuK4wnuqiY0R1w",
      "scanned_at": "2026-07-15T02:15:11.015748Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "1697d205cd4ba7f610e1ef8898eea5c84881d657dad16022fe416b0c805a7025"
    },
    {
      "model_id": "conjuncts/ditr-e15",
      "scanned_at": "2026-07-15T02:15:13.784675Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).  - **Hardware Type:** [More"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/table-transformer-structure-recognition-v1.1-all",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/table-transformer-structure-recognition-v1.1-all"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "table-transformer",
          "confidence": 0.5,
          "raw_context": "model_type: table-transformer"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.35,
      "provenance_hash": "fe92489bcad3335c76804a0849e2d57a4dc7d5cf80001f6e317a073f6d6bbab9"
    },
    {
      "model_id": "cooperdk/MGE-GemmaWild-8b-checkpoints",
      "scanned_at": "2026-07-15T02:15:16.540093Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "494e04e97e48d533747aba31646b51213077924b1cbbf2fb8ffc28ca945e5395"
    },
    {
      "model_id": "cooperdk/MGE-qwen2.5-vl-7b-checkpoints",
      "scanned_at": "2026-07-15T02:15:19.272129Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b8bad6b6626f457ff0408f11b9a912cdbbcc39bfcdca910c125904a4488f0df1"
    },
    {
      "model_id": "core-outline/tapas-large-finetuned-wtq",
      "scanned_at": "2026-07-15T02:15:22.006023Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "google/tapas-large-finetuned-wtq",
          "confidence": 0.9,
          "raw_context": "_name_or_path: google/tapas-large-finetuned-wtq"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "tapas",
          "confidence": 0.5,
          "raw_context": "model_type: tapas"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "fa935d861241d0a2755b83dab3147db1af5b341bcaa60c7df51fe30182b3f538"
    },
    {
      "model_id": "coreml-projects/DepthPro-coreml",
      "scanned_at": "2026-07-15T02:15:24.830290Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "apple/DepthPro",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:apple/DepthPro"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:apple/DepthPro",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:apple/DepthPro"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "th on a single image.\r \r [DepthPro paper](https://arxiv.org/pdf/2410.02073)\r \r [DepthPro original repo](h"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:apple/DepthPro",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "cular Metric Depth in Less Than a Second](https://arxiv.org/abs/2410.02073)**, by *Aleksei Bochkovskii, A"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "apple/DepthPro",
      "base_model_chain": [
        "apple/DepthPro"
      ],
      "training_section_present": false,
      "license": "apple-ascl",
      "provenance_score": 0.25,
      "provenance_hash": "b205e81cf298aa7f00ea5f1c34779a6ac0ab8c11e39e79b24e4c0224cbf07979"
    },
    {
      "model_id": "corzent/yolo11x_watermark_detection",
      "scanned_at": "2026-07-15T02:15:29.410348Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.1,
      "provenance_hash": "b2ebd7bee17ceff660404d814defa39c003147d6d0d7b87090a0b53107ed17fc"
    },
    {
      "model_id": "cotxuyenkieu/DNAtVqy10JWB6Lj",
      "scanned_at": "2026-07-15T02:15:32.158236Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "88c840de49cdcf54beca8faa114c8a208137e55a5833c7f53fd01526f243ffb8"
    },
    {
      "model_id": "cross-encoder/nli-MiniLM2-L6-H768",
      "scanned_at": "2026-07-15T02:15:34.914661Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "nyu-mll/multi_nli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:nyu-mll/multi_nli"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "stanfordnlp/snli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:stanfordnlp/snli"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large",
          "confidence": 0.9,
          "raw_context": "_name_or_path: nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "roberta",
          "confidence": 0.5,
          "raw_context": "model_type: roberta"
        }
      ],
      "declared_datasets": [
        "stanfordnlp/snli",
        "nyu-mll/multi_nli"
      ],
      "inferred_datasets": [],
      "base_model": "nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large",
      "base_model_chain": [
        "nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.7,
      "provenance_hash": "c532c00b45e67815c09e11a0abc261dc9769f3fbe95e6e57ce1d6d7f73fd6a7c"
    },
    {
      "model_id": "cross-encoder/nli-deberta-base",
      "scanned_at": "2026-07-15T02:15:39.474898Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "nyu-mll/multi_nli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:nyu-mll/multi_nli"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "stanfordnlp/snli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:stanfordnlp/snli"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "microsoft/deberta-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:microsoft/deberta-base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:microsoft/deberta-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:microsoft/deberta-base"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/deberta-base",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/deberta-base"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deberta",
          "confidence": 0.5,
          "raw_context": "model_type: deberta"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-base",
          "value": "squad",
          "confidence": 0.5599999999999999,
          "raw_context": "uning on NLU tasks  We present the dev results on SQuAD 1.1/2.0 and MNLI tasks.  | Model             | SQ"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "RT with Disentangled Attention  [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa"
        }
      ],
      "declared_datasets": [
        "stanfordnlp/snli",
        "nyu-mll/multi_nli"
      ],
      "inferred_datasets": [
        "squad",
        "arxiv"
      ],
      "base_model": "microsoft/deberta-base",
      "base_model_chain": [
        "microsoft/deberta-base"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.7999999999999999,
      "provenance_hash": "2eacee9adac52e7aa37d97fb8ae6ea7d2656215daf7d2f5baabd6cf57dd19481"
    },
    {
      "model_id": "cross-encoder/nli-deberta-v3-base",
      "scanned_at": "2026-07-15T02:15:44.070130Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "nyu-mll/multi_nli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:nyu-mll/multi_nli"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "stanfordnlp/snli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:stanfordnlp/snli"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "microsoft/deberta-v3-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:microsoft/deberta-v3-base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:microsoft/deberta-v3-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:microsoft/deberta-v3-base"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "microsoft/deberta-v3-base",
          "confidence": 0.85,
          "raw_context": "s/cross-encoder/README.html) class. This model is based on [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/deberta-v3-base",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/deberta-v3-base"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deberta-v2",
          "confidence": 0.5,
          "raw_context": "model_type: deberta-v2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-base",
          "value": "voc",
          "confidence": 0.5599999999999999,
          "raw_context": "768. It has only 86M backbone parameters  with a vocabulary containing 128K tokens which introduces 98"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-base",
          "value": "squad",
          "confidence": 0.5599999999999999,
          "raw_context": "uning on NLU tasks  We present the dev results on SQuAD 2.0 and MNLI tasks.  | Model             |Vocabul"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-base",
          "value": "glue",
          "confidence": 0.5599999999999999,
          "raw_context": "buted.launch --nproc_per_node=${num_gpus} \\   run_glue.py \\   --model_name_or_path microsoft/deberta-v3-"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "Disentangled Embedding Sharing  [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa"
        }
      ],
      "declared_datasets": [
        "stanfordnlp/snli",
        "nyu-mll/multi_nli"
      ],
      "inferred_datasets": [
        "glue",
        "voc",
        "squad",
        "arxiv"
      ],
      "base_model": "microsoft/deberta-v3-base",
      "base_model_chain": [
        "microsoft/deberta-v3-base"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "8341542cc2171b0c41e7b63dcf59085facf33f240522336dbe0ed3c414bd243b"
    },
    {
      "model_id": "cross-encoder/nli-deberta-v3-large",
      "scanned_at": "2026-07-15T02:15:48.658743Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "nyu-mll/multi_nli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:nyu-mll/multi_nli"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "stanfordnlp/snli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:stanfordnlp/snli"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "microsoft/deberta-v3-large",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:microsoft/deberta-v3-large"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:microsoft/deberta-v3-large",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:microsoft/deberta-v3-large"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "microsoft/deberta-v3-large",
          "confidence": 0.85,
          "raw_context": "s/cross-encoder/README.html) class. This model is based on [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-larg"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/deberta-v3-large",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/deberta-v3-large"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deberta-v2",
          "confidence": 0.5,
          "raw_context": "model_type: deberta-v2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-large",
          "value": "voc",
          "confidence": 0.5599999999999999,
          "raw_context": "of 1024. It has 304M backbone parameters  with a vocabulary containing 128K tokens which introduces 13"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-large",
          "value": "squad",
          "confidence": 0.5599999999999999,
          "raw_context": "uning on NLU tasks  We present the dev results on SQuAD 2.0 and MNLI tasks.  | Model             |Vocabul"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-large",
          "value": "glue",
          "confidence": 0.5599999999999999,
          "raw_context": "buted.launch --nproc_per_node=${num_gpus} \\   run_glue.py \\   --model_name_or_path microsoft/deberta-v3-"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-large",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "Disentangled Embedding Sharing  [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa"
        }
      ],
      "declared_datasets": [
        "stanfordnlp/snli",
        "nyu-mll/multi_nli"
      ],
      "inferred_datasets": [
        "glue",
        "voc",
        "squad",
        "arxiv"
      ],
      "base_model": "microsoft/deberta-v3-large",
      "base_model_chain": [
        "microsoft/deberta-v3-large"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "5d32e456c77458b0268a12a114b08286e7452a1e6a20b73751004870bcef5f3e"
    },
    {
      "model_id": "cross-encoder/nli-deberta-v3-xsmall",
      "scanned_at": "2026-07-15T02:15:53.272903Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "nyu-mll/multi_nli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:nyu-mll/multi_nli"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "stanfordnlp/snli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:stanfordnlp/snli"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "microsoft/deberta-v3-xsmall",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:microsoft/deberta-v3-xsmall"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:microsoft/deberta-v3-xsmall",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:microsoft/deberta-v3-xsmall"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "microsoft/deberta-v3-xsmall",
          "confidence": 0.85,
          "raw_context": "s/cross-encoder/README.html) class. This model is based on [microsoft/deberta-v3-xsmall](https://huggingface.co/microsoft/deberta-v3-xsma"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/deberta-v3-xsmall",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/deberta-v3-xsmall"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deberta-v2",
          "confidence": 0.5,
          "raw_context": "model_type: deberta-v2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-xsmall",
          "value": "voc",
          "confidence": 0.5599999999999999,
          "raw_context": ". It has only **22M** backbone parameters  with a vocabulary containing 128K tokens which introduces 48"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-xsmall",
          "value": "squad",
          "confidence": 0.5599999999999999,
          "raw_context": "uning on NLU tasks  We present the dev results on SQuAD 2.0 and MNLI tasks.  | Model             |Vocabul"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-xsmall",
          "value": "glue",
          "confidence": 0.5599999999999999,
          "raw_context": "buted.launch --nproc_per_node=${num_gpus} \\   run_glue.py \\   --model_name_or_path microsoft/deberta-v3-"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:microsoft/deberta-v3-xsmall",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "Disentangled Embedding Sharing  [DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa"
        }
      ],
      "declared_datasets": [
        "stanfordnlp/snli",
        "nyu-mll/multi_nli"
      ],
      "inferred_datasets": [
        "glue",
        "voc",
        "squad",
        "arxiv"
      ],
      "base_model": "microsoft/deberta-v3-xsmall",
      "base_model_chain": [
        "microsoft/deberta-v3-xsmall"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "f36945e5bd53f8e677ab3a18a3be7807e8691321b4b39491ec83dd995405f40c"
    },
    {
      "model_id": "cross-encoder/nli-distilroberta-base",
      "scanned_at": "2026-07-15T02:15:57.839545Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "nyu-mll/multi_nli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:nyu-mll/multi_nli"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "stanfordnlp/snli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:stanfordnlp/snli"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "distilbert/distilroberta-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:distilbert/distilroberta-base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:distilbert/distilroberta-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:distilbert/distilroberta-base"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "roberta",
          "confidence": 0.5,
          "raw_context": "model_type: roberta"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:distilbert/distilroberta-base",
          "value": "openwebtext",
          "confidence": 0.48,
          "raw_context": "n tags: - exbert  license: apache-2.0 datasets: - openwebtext ---  # Model Card for DistilRoBERTa base  # Table"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:distilbert/distilroberta-base",
          "value": "glue",
          "confidence": 0.5599999999999999,
          "raw_context": "ples/research_projects/distillation/README.md)):  Glue test results:  | Task | MNLI | QQP  | QNLI | SST-"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:distilbert/distilroberta-base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "llation/README.md)   - [Associated Paper](https://arxiv.org/abs/1910.01108)    # Uses  ## Direct Use and"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:distilbert/distilroberta-base",
          "value": "openwebtext",
          "confidence": 0.5599999999999999,
          "raw_context": "n tags: - exbert  license: apache-2.0 datasets: - openwebtext ---  # Model Card for DistilRoBERTa base  # Table"
        }
      ],
      "declared_datasets": [
        "stanfordnlp/snli",
        "nyu-mll/multi_nli"
      ],
      "inferred_datasets": [
        "glue",
        "arxiv",
        "openwebtext"
      ],
      "base_model": "distilbert/distilroberta-base",
      "base_model_chain": [
        "distilbert/distilroberta-base"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.85,
      "provenance_hash": "9815eb33e6f368e8b3f15780858f9ad010e4faa10c30c92dee6bb282bcd7deae"
    },
    {
      "model_id": "cross-encoder/nli-roberta-base",
      "scanned_at": "2026-07-15T02:16:02.412640Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "nyu-mll/multi_nli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:nyu-mll/multi_nli"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "stanfordnlp/snli",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:stanfordnlp/snli"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "FacebookAI/roberta-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:FacebookAI/roberta-base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:FacebookAI/roberta-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:FacebookAI/roberta-base"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "roberta",
          "confidence": 0.5,
          "raw_context": "model_type: roberta"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "reunion of five",
          "confidence": 0.48,
          "raw_context": "s model.  ## Training data  The RoBERTa model was pretrained on the reunion of five datasets: - [BookCorpus](https://yknzhu.wixsite.com/mbweb"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "bookcorpus",
          "confidence": 0.48,
          "raw_context": "guage: en tags: - exbert license: mit datasets: - bookcorpus - wikipedia ---  # RoBERTa base model  Pretrained"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "wikipedia",
          "confidence": 0.48,
          "raw_context": "s: - exbert license: mit datasets: - bookcorpus - wikipedia ---  # RoBERTa base model  Pretrained model on En"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "commoncrawl",
          "confidence": 0.48,
          "raw_context": "lists, tables and headers) ; - [CC-News](https://commoncrawl.org/2016/10/news-dataset-available/), a dataset c"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "OpenWebText",
          "confidence": 0.48,
          "raw_context": "wled between September 2016 and February 2019. - [OpenWebText](https://github.com/jcpeterson/openwebtext), an o"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "voc",
          "confidence": 0.5599999999999999,
          "raw_context": "a byte version of Byte-Pair Encoding (BPE) and a vocabulary size of 50,000. The inputs of the model ta"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "bookcorpus",
          "confidence": 0.5599999999999999,
          "raw_context": "guage: en tags: - exbert license: mit datasets: - bookcorpus - wikipedia ---  # RoBERTa base model  Pretrained"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "glue",
          "confidence": 0.5599999999999999,
          "raw_context": "asks, this model achieves the following results:  Glue test results:  | Task | MNLI | QQP  | QNLI | SST-"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "ective. It was introduced in [this paper](https://arxiv.org/abs/1907.11692) and first released in [this r"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "openwebtext",
          "confidence": 0.5599999999999999,
          "raw_context": "wled between September 2016 and February 2019. - [OpenWebText](https://github.com/jcpeterson/openwebtext), an o"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:FacebookAI/roberta-base",
          "value": "wikipedia",
          "confidence": 0.5599999999999999,
          "raw_context": "s: - exbert license: mit datasets: - bookcorpus - wikipedia ---  # RoBERTa base model  Pretrained model on En"
        }
      ],
      "declared_datasets": [
        "stanfordnlp/snli",
        "nyu-mll/multi_nli"
      ],
      "inferred_datasets": [
        "glue",
        "OpenWebText",
        "commoncrawl",
        "wikipedia",
        "voc",
        "arxiv",
        "openwebtext",
        "bookcorpus",
        "reunion of five"
      ],
      "base_model": "FacebookAI/roberta-base",
      "base_model_chain": [
        "FacebookAI/roberta-base"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8999999999999999,
      "provenance_hash": "efbec96f548196f7afcf331aa6d59831c89f77e5f4706446205ba48c50cabf0d"
    },
    {
      "model_id": "cryptonesian/largest",
      "scanned_at": "2026-07-15T02:16:07.913922Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b4b4c75753b3051bf0edec593d22cc1a774c904f2e3a80407bd320cf7d6bf99c"
    },
    {
      "model_id": "cryptonesian/longers",
      "scanned_at": "2026-07-15T02:16:10.837367Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "4001111691e01bccdd66d21930de6fcab161568ed6e257fee9d549457477a19e"
    },
    {
      "model_id": "cryptonesian/mediumwell",
      "scanned_at": "2026-07-15T02:16:13.628851Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "c8ab36163b63bb0ea22ad85b256b0d79bb00009ffe300797e33114dc8882484f"
    },
    {
      "model_id": "cslys1999/Eureka-Audio-Instruct",
      "scanned_at": "2026-07-15T02:16:16.391529Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-1.7B-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-1.7B-Base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Qwen/Qwen3-1.7B-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Qwen/Qwen3-1.7B-Base"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "audio/wav",
          "confidence": 0.8,
          "raw_context": "/example.com/audio.wav\"` - **Base64 data URI**: `\"data:audio/wav;base64,<base64_string>\"`  Supported audio formats"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "\"ModelScope\"/>   </a>   &nbsp;   <a href=\"https://arxiv.org/abs/2602.13954\">     <img src=\"https://img.sh"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-1.7B-Base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [
        "audio/wav"
      ],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-1.7B-Base",
      "base_model_chain": [
        "Qwen/Qwen3-1.7B-Base"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.35000000000000003,
      "provenance_hash": "3293cdb2959ebbad88dda270d3aacbbd60f35500cbcad7297c494634cc4b1e2c"
    },
    {
      "model_id": "csukuangfj2/onnxruntime-libs",
      "scanned_at": "2026-07-15T02:16:20.970043Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "000ab8376e251e1ccddaeef44d4dcebdf0cac30fa998d1ae31361a3fbf3f2325"
    },
    {
      "model_id": "csukuangfj2/sherpa-onnx-fire-red-asr2-ctc-zh_en-2026-02-25",
      "scanned_at": "2026-07-15T02:16:23.727461Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "bfb53b3bcc6dfea193029304f5572e04d3c5280b12d42547f9f1eb0f28600d0c"
    },
    {
      "model_id": "curiousily/Llama-3-8B-Instruct-Finance-RAG",
      "scanned_at": "2026-07-15T02:16:26.486997Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "virattt/financial-qa-10K",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:virattt/financial-qa-10K"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "meta-llama/Meta-Llama-3-8B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:meta-llama/Meta-Llama-3-8B-Instruct"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:meta-llama/Meta-Llama-3-8B-Instruct",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "virattt/financial-qa-10K",
          "confidence": 0.8,
          "raw_context": "ma-3-8B-Instruct) model on 4000 examples from the [virattt/financial-qa-10K](https://huggingface.co/datasets/virattt/financial-qa-10K) dataset.  The model is f"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "meta-llama/Meta-Llama-3-8B-Instruct",
          "confidence": 0.85,
          "raw_context": "ame: transformers tags: - finance license: llama3 base_model: meta-llama/Meta-Llama-3-8B-Instruct datasets: - virattt/financial-qa-10K language: -"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "meta-llama/Meta-Llama-3-8B-Instruct",
          "confidence": 0.9,
          "raw_context": "_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [
        "virattt/financial-qa-10K"
      ],
      "inferred_datasets": [],
      "base_model": "meta-llama/Meta-Llama-3-8B-Instruct",
      "base_model_chain": [
        "meta-llama/Meta-Llama-3-8B-Instruct"
      ],
      "training_section_present": false,
      "license": "llama3",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "c52e3e5efaec032c92a3e385120600099a4bc5caf6ba097eead2b6819b4e6b19"
    },
    {
      "model_id": "curiousily/Llama-3.2-1B-Mental-Health-Sentiment",
      "scanned_at": "2026-07-15T02:16:31.121814Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "an offline",
          "confidence": 0.6,
          "raw_context": "Sept 25, 2024  **Status:** This is a static model trained on an offline dataset. Future versions may be released that improve mod"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "squad",
          "confidence": 0.7,
          "raw_context": "| 32.8 | 69.1 | 79.7 | | Reading comprehension | SQuAD | 1 | em | 49.2 | 67.7 | 77 | |  | QuAC (F1) | 1"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "enhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasi"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikitext",
          "confidence": 0.7,
          "raw_context": "ng 800 samples with sequence-length 2048 from the WikiText 2 dataset. For GPTQ, we used 128 samples from the"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "squad",
        "arxiv",
        "wikitext"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "llama3.2",
      "provenance_score": 0.55,
      "provenance_hash": "575a32e7291b44280024e3edac5567cee2f8c1bedcad22cb60687edd504ac39d"
    },
    {
      "model_id": "curiousily/falcon-7b-qlora-chat-support-bot-faq-merged",
      "scanned_at": "2026-07-15T02:16:33.903980Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "Tube tutorial](https://www.youtube.com/watch?v=DcBC4yGHV4Q) - Deploy LLM on Inference Endpoints tutori"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "/falcon-7b) model fine-tuned with [QLoRA](https://arxiv.org/abs/2305.14314) on a custom e-commerce chatbo"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "tiiuae/falcon-7b",
          "confidence": 0.9,
          "raw_context": "_name_or_path: tiiuae/falcon-7b"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "RefinedWebModel",
          "confidence": 0.5,
          "raw_context": "model_type: RefinedWebModel"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "bce929a31e913c8bcdaab560f08bd5fefc77623e57149e3099b4ee1852db30ad"
    },
    {
      "model_id": "curiousily/layoutlmv3-financial-document-classification",
      "scanned_at": "2026-07-15T02:16:36.828096Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/layoutlmv3-base",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/layoutlmv3-base"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "layoutlmv3",
          "confidence": 0.5,
          "raw_context": "model_type: layoutlmv3"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "cc-by-nc-sa-4.0",
      "provenance_score": 0.4,
      "provenance_hash": "8f63bd4f5bb32eb030479676e05fea9743513d0a348d9d24692324eb5590e7e0"
    },
    {
      "model_id": "curiousily/tiny-crypto-sentiment-analysis",
      "scanned_at": "2026-07-15T02:16:39.577740Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
          "confidence": 0.85,
          "raw_context": "ers tags: - finance pipeline_tag: text-generation base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T ---  # Tiny Crypto Sentiment Analysis  Fine-tuned"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
          "confidence": 0.9,
          "raw_context": "_name_or_path: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
          "value": "here",
          "confidence": 0.48,
          "raw_context": "en_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TinyLlama__TinyLlama-"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
          "value": "SlimPajama",
          "confidence": 0.48,
          "raw_context": "ge: - en license: apache-2.0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata model-index: - name:"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
          "value": "starcoder",
          "confidence": 0.48,
          "raw_context": ".0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata model-index: - name: TinyLlama-1.1B-intermedi"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
          "value": "slimpajama",
          "confidence": 0.5599999999999999,
          "raw_context": "ge: - en license: apache-2.0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata model-index: - name:"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
          "value": "starcoder",
          "confidence": 0.5599999999999999,
          "raw_context": ".0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata model-index: - name: TinyLlama-1.1B-intermedi"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "here",
        "SlimPajama",
        "slimpajama",
        "starcoder"
      ],
      "base_model": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
      "base_model_chain": [
        "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.4,
      "provenance_hash": "bb89ee5951e10cd42a70a3cda4574edbf72caff25ac3ae937ac686303dd87ef0"
    },
    {
      "model_id": "currentfear/qwen_devolution_full_16bit",
      "scanned_at": "2026-07-15T02:16:44.157010Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit",
          "confidence": 0.85,
          "raw_context": "--- base_model: unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3_vl",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3_vl"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit",
      "base_model_chain": [
        "unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit",
        "Qwen/Qwen3-VL-8B-Instruct"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.25,
      "provenance_hash": "991536a445734d9afbffec2b51e2306e64b3cdc7a82d4abc7ff7c3f49806ade1"
    },
    {
      "model_id": "cyberagent/layerd-birefnet",
      "scanned_at": "2026-07-15T02:16:49.859010Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "D BiRefNet Matting Module  <div align=\"left\">  [![arxiv paper](https://img.shields.io/badge/arxiv-paper-o"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "ZhengPeng7/BiRefNet",
          "confidence": 0.9,
          "raw_context": "_name_or_path: ZhengPeng7/BiRefNet"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "5d317ea5a331917dea10ff4022f9e7759667785c92f4faf0fea3e3548365948a"
    },
    {
      "model_id": "da1ch812/advanced-comp-model-20260301141942",
      "scanned_at": "2026-07-15T02:16:52.681939Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "u-10bei/sft_alfworld_trajectory_dataset_v2",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:u-10bei/sft_alfworld_trajectory_dataset_v2"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "u-10bei/sft_alfworld_trajectory_dataset_v3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:u-10bei/sft_alfworld_trajectory_dataset_v3"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "u-10bei/sft_alfworld_trajectory_dataset_v4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:u-10bei/sft_alfworld_trajectory_dataset_v4"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "u-10bei/sft_alfworld_trajectory_dataset_v5",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:u-10bei/sft_alfworld_trajectory_dataset_v5"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "u-10bei/dbbench_sft_dataset_react",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:u-10bei/dbbench_sft_dataset_react"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "u-10bei/dbbench_sft_dataset_react_v2",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:u-10bei/dbbench_sft_dataset_react_v2"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "u-10bei/dbbench_sft_dataset_react_v3",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:u-10bei/dbbench_sft_dataset_react_v3"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "u-10bei/dbbench_sft_dataset_react_v4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:u-10bei/dbbench_sft_dataset_react_v4"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "unsloth/Qwen3-4B-Instruct-2507",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:unsloth/Qwen3-4B-Instruct-2507"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:unsloth/Qwen3-4B-Instruct-2507",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:unsloth/Qwen3-4B-Instruct-2507"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "unsloth/Qwen3-4B-Instruct-2507",
          "confidence": 0.85,
          "raw_context": "--- base_model: unsloth/Qwen3-4B-Instruct-2507 datasets: - u-10bei/sft_alfworld_trajectory_datas"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "unsloth/Qwen3-4B-Instruct-2507",
          "confidence": 0.85,
          "raw_context": "covery from errors.  ## Training Configuration  - Base model: unsloth/Qwen3-4B-Instruct-2507 - Method: LoRA   - dtype: torch.bfloat16   - load"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:unsloth/Qwen3-4B-Instruct-2507",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [
        "u-10bei/dbbench_sft_dataset_react",
        "u-10bei/dbbench_sft_dataset_react_v2",
        "u-10bei/sft_alfworld_trajectory_dataset_v2",
        "u-10bei/sft_alfworld_trajectory_dataset_v3",
        "u-10bei/sft_alfworld_trajectory_dataset_v4",
        "u-10bei/sft_alfworld_trajectory_dataset_v5",
        "u-10bei/dbbench_sft_dataset_react_v4",
        "u-10bei/dbbench_sft_dataset_react_v3"
      ],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "unsloth/Qwen3-4B-Instruct-2507",
      "base_model_chain": [
        "unsloth/Qwen3-4B-Instruct-2507",
        "Qwen/Qwen3-4B-Instruct-2507"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.85,
      "provenance_hash": "6f65ed1eaee5b436e4b04ef03b1584c3aaf152a3904afd694285d0efd249fc79"
    },
    {
      "model_id": "dac-purcl/math_joint_nonorm_dbdk2.0to1.0_cosine_logfac8_k2_beta1e-3",
      "scanned_at": "2026-07-15T02:16:58.188304Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b5bc10f414423b629d830ae4b546da315ea4c2574a1b0862eb0852f2ccbf591b"
    },
    {
      "model_id": "damcongduong55/1Bu8KC5UsMkhP1S",
      "scanned_at": "2026-07-15T02:17:00.945907Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "819619084140e0d74993387ebfb56d562b3c64bc2ea76de97bee5bb1d5520f36"
    },
    {
      "model_id": "damcongduong55/aWrtADMaCjo6D75",
      "scanned_at": "2026-07-15T02:17:03.677016Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "976f886ae37db78d79a03245ef6e363cff6d9982c61487fe93ecc2707d0f0c65"
    },
    {
      "model_id": "damcongduong55/jBGcQaMCrmAmpbD",
      "scanned_at": "2026-07-15T02:17:06.412886Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "01cce449952cebc9b548fa122fc3b6fc6830b8fbdad13649db394ef09d3441b6"
    },
    {
      "model_id": "damir-hi/layoutlmv2-base-uncased_finetuned_docvqa",
      "scanned_at": "2026-07-15T02:17:09.150352Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/layoutlmv2-base-uncased",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/layoutlmv2-base-uncased"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "layoutlmv2",
          "confidence": 0.5,
          "raw_context": "model_type: layoutlmv2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b62139281355232e7d8ae0ff802a9c2583d21f0422a9755e6c614bae3a8d8788"
    },
    {
      "model_id": "danbrown/Lyriel-v1-5",
      "scanned_at": "2026-07-15T02:17:11.904689Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "ee5b5e74295368b472d908856496830354e6fb1010599dcdac39f6f022bf9f55"
    },
    {
      "model_id": "dandelin/vilt-b32-mlm",
      "scanned_at": "2026-07-15T02:17:14.750786Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "mlm_logits = outputs.logits[0]  # shape (seq_len, vocab_size)         # only take into account text fea"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "coco",
          "confidence": 0.7,
          "raw_context": "e Transformer (ViLT) model pre-trained on GCC+SBU+COCO+VG (200k steps). It was introduced in the paper ["
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ithout Convolution or Region Supervision](https://arxiv.org/abs/2102.03334) by Kim et al. and first relea"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "vilt",
          "confidence": 0.5,
          "raw_context": "model_type: vilt"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "coco",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.55,
      "provenance_hash": "4f6f68c1836d26df090a3448abb630db92898cf8e5e4a685faef4094a080ce06"
    },
    {
      "model_id": "dangvantuan/sentence-camembert-large",
      "scanned_at": "2026-07-15T02:17:17.495558Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "stsb_multi_mt",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:stsb_multi_mt"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "stsb",
          "confidence": 0.6,
          "raw_context": "transformers'](https://www.sbert.net/) on dataset [stsb](https://huggingface.co/datasets/stsb_multi_mt/viewer/fr/train)   ## Usage The mode"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ls Reimers, Iryna Gurevych}, \t   journal={https://arxiv.org/abs/1908.10084}, \t   year={2019} \t}   \t@artic"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "camembert/camembert-large",
          "confidence": 0.9,
          "raw_context": "_name_or_path: camembert/camembert-large"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "camembert",
          "confidence": 0.5,
          "raw_context": "model_type: camembert"
        }
      ],
      "declared_datasets": [
        "stsb_multi_mt"
      ],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.25,
      "provenance_hash": "1160fe8e55fe4751011976fd880c33fc4c9525a25fa4ee871a5f4d1565513384"
    },
    {
      "model_id": "dangvantuan/vietnamese-embedding",
      "scanned_at": "2026-07-15T02:17:20.238162Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "ViNLI-SimCSE-supervised",
          "confidence": 0.6,
          "raw_context": "stages: #### Stage 1: Initial Training - Dataset: [ViNLI-SimCSE-supervised](https://huggingface.co/datasets/anti-ai/ViNLI-SimCSE-supervised) - Method: Trained"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "STSB-vn",
          "confidence": 0.6,
          "raw_context": "ic Textual Similarity on STS Benchmark - Dataset: [STSB-vn](https://huggingface.co/datasets/doanhieung/vi-stsbenchmark) - Method: Fine-tuning"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "thod: Trained using the [SimCSE approach](https://arxiv.org/abs/2104.08821) which employs a supervised co"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "./vietnamese-embedding/",
          "confidence": 0.9,
          "raw_context": "_name_or_path: ./vietnamese-embedding/"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "roberta",
          "confidence": 0.5,
          "raw_context": "model_type: roberta"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.45,
      "provenance_hash": "738e75cbaec22688fd345cd40c78b917b191c97f203cd85c2605824ee033b8eb"
    },
    {
      "model_id": "dangvinh77/uYouPlus",
      "scanned_at": "2026-07-15T02:17:22.998664Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "f5ad0ec0f1d7a98bb5fb9958fae07f890d5763b9ffdcfa6c8e02972ecf1b0ffb"
    },
    {
      "model_id": "dangxuanlanh29/OPcAv2HYP3tLxqb",
      "scanned_at": "2026-07-15T02:17:25.754550Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b267e3975bd2ba6efca61d7ae96c6ee809512793952e874cedcb234e68ea3405"
    },
    {
      "model_id": "dangxuanlanh29/n8k7VZzQZxPKg6S",
      "scanned_at": "2026-07-15T02:17:28.490648Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "4c9a485ebc306c9174cede7df0d3e7791b3217d5ad88e3823c7c7d94bb5c83ba"
    },
    {
      "model_id": "dangxuanlanh29/yUWkzNak4NnZTVO",
      "scanned_at": "2026-07-15T02:17:31.225498Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "c638cb0e7c551ccb50f9ea1a443729543309205f7a89d0500dd51af6020246f6"
    },
    {
      "model_id": "danielheinz/e5-base-sts-en-de",
      "scanned_at": "2026-07-15T02:17:33.956246Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deutsche-telekom/ger-backtrans-paraphrase",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deutsche-telekom/ger-backtrans-paraphrase"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "paws-x",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:paws-x"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "stsb_multi_mt",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:stsb_multi_mt"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "paws-x",
          "confidence": 0.6,
          "raw_context": "sets/deutsche-telekom/ger-backtrans-paraphrase) - [paws-x](https://huggingface.co/datasets/paws-x) - [stsb_multi_mt](https://huggingface.co/d"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "stsb_multi_mt",
          "confidence": 0.6,
          "raw_context": "paws-x](https://huggingface.co/datasets/paws-x) - [stsb_multi_mt](https://huggingface.co/datasets/stsb_multi_mt)  The training procedure can be divi"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "German subsets of the following",
          "confidence": 0.6,
          "raw_context": "ty in mind.  ## Model Training The model has been fine-tuned on the German subsets of the following datasets: - [German paraphrase corpus by Philip May](http"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/root/.cache/torch/sentence_transformers/intfloat_multilingual-e5-base/",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /root/.cache/torch/sentence_transformers/intfloat_multilingual-e5-base/"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "xlm-roberta",
          "confidence": 0.5,
          "raw_context": "model_type: xlm-roberta"
        }
      ],
      "declared_datasets": [
        "paws-x",
        "stsb_multi_mt",
        "deutsche-telekom/ger-backtrans-paraphrase"
      ],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.4,
      "provenance_hash": "060a342f14f47e24b5413a422cbbdbe32d4378c4d2b96eed82c1d568f84af4fe"
    },
    {
      "model_id": "danushkv/medgemma-cholec-inst",
      "scanned_at": "2026-07-15T02:17:36.702084Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:google/medgemma-1.5-4b-it",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:google/medgemma-1.5-4b-it"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "google/medgemma-1.5-4b-it",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:google/medgemma-1.5-4b-it"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "google/medgemma-1.5-4b-it",
          "confidence": 0.85,
          "raw_context": "--- base_model: google/medgemma-1.5-4b-it library_name: peft pipeline_tag: text-generation"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "adapter:google/medgemma-1.5-4b-it",
      "base_model_chain": [
        "adapter:google/medgemma-1.5-4b-it"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.4,
      "provenance_hash": "1161ff77c796f5778c7ff0f22b3c486b80602118567e0d6df2bb4eddca03e552"
    },
    {
      "model_id": "darask0/ownLora",
      "scanned_at": "2026-07-15T02:17:41.275275Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "34d98ed11d1c5365f292f5ffc27bfc454c326075203a0ddb37ce6be2ff605e82"
    },
    {
      "model_id": "dare43321/hindi-tts-model",
      "scanned_at": "2026-07-15T02:17:44.032518Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "canopylabs/3b-hi-ft-research_release",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:canopylabs/3b-hi-ft-research_release"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:canopylabs/3b-hi-ft-research_release",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:canopylabs/3b-hi-ft-research_release"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "canopylabs/3b-hi-ft-research_release",
          "confidence": 0.85,
          "raw_context": "--- base_model: canopylabs/3b-hi-ft-research_release tags: - text-generation-inference - transformers"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "canopylabs/3b-hi-ft-research_release",
      "base_model_chain": [
        "canopylabs/3b-hi-ft-research_release",
        "canopylabs/orpheus-3b-0.1-pretrained",
        "meta-llama/Llama-3.2-3B-Instruct"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "27c4e5cb550a2e5a9b381517b963e04934cdb2e236f579ab4a412c59329c08cd"
    },
    {
      "model_id": "dark-side-of-the-code/Llama-3.2-11B-Vision-Instruct-GPTQ",
      "scanned_at": "2026-07-15T02:17:48.626090Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "381ffdfa8bd08176b0e4d3b9c3b5a50b74195bde7726c33eb7eab8cc326126c5"
    },
    {
      "model_id": "data-analytics/flat",
      "scanned_at": "2026-07-15T02:17:51.388517Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "gpl-3.0",
      "provenance_score": 0.1,
      "provenance_hash": "acc2474303f973b370c7d5b2de4b0127f2fc6925ddd4df674ba2f4435e4e9617"
    },
    {
      "model_id": "dataautogpt3/ProteusV0.2",
      "scanned_at": "2026-07-15T02:17:54.206563Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "oscar",
          "confidence": 0.7,
          "raw_context": "otion Picture Film: (Sharp Detailed Image) An     Oscar winning movie for Best Cinematography a woman in"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "oscar"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "gpl-3.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "cc74dc763bd4b1884e06ca2fd57eea9a3c5b1392ca4597fafdd5c3f9f205ac03"
    },
    {
      "model_id": "dataautogpt3/ProteusV0.3",
      "scanned_at": "2026-07-15T02:17:56.963926Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "gpl-3.0",
      "provenance_score": 0.1,
      "provenance_hash": "1ea4a303cb448a029eb6f16526ff9c468c9ace9207513f4993ef35eb0ab02af9"
    },
    {
      "model_id": "dbmdz/bert-base-italian-xxl-uncased",
      "scanned_at": "2026-07-15T02:17:59.723508Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "wikipedia",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:wikipedia"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.6,
          "raw_context": "--- language: it license: mit datasets: - wikipedia ---  # 🤗 + 📚 dbmdz BERT and ELECTRA models  In th"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "138,379,147 tokens.  Note: Unfortunately, a wrong vocab size was used when training the XXL models. Thi"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "oscar",
          "confidence": 0.7,
          "raw_context": "extend it with data from the Italian part of the [OSCAR corpus](https://traces1.inria.fr/oscar/). Thus, t"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.7,
          "raw_context": "--- language: it license: mit datasets: - wikipedia ---  # 🤗 + 📚 dbmdz BERT and ELECTRA models  In th"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bert",
          "confidence": 0.5,
          "raw_context": "model_type: bert"
        }
      ],
      "declared_datasets": [
        "wikipedia"
      ],
      "inferred_datasets": [
        "voc",
        "wikipedia",
        "oscar"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.35000000000000003,
      "provenance_hash": "ff7ef54b1bda5858792344bbad08e7488583eec880bb0e9454fdf8040c43e19c"
    },
    {
      "model_id": "dboris/nemotron-asr-mlx",
      "scanned_at": "2026-07-15T02:18:02.474822Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "librispeech_asr",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:librispeech_asr"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "LIUM/tedlium",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:LIUM/tedlium"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ased on [Cache-aware Streaming Conformer](https://arxiv.org/abs/2312.17279) and the [NeMo](https://github"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "nemotron_asr",
          "confidence": 0.5,
          "raw_context": "model_type: nemotron_asr"
        }
      ],
      "declared_datasets": [
        "librispeech_asr",
        "LIUM/tedlium"
      ],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.35000000000000003,
      "provenance_hash": "0b194440f09301f56d0f09a100f342f67409ab75f24d0ace866080fa5a4caad5"
    },
    {
      "model_id": "decoderesearch/synth-sae-bench-16k-v1-saes",
      "scanned_at": "2026-07-15T02:18:05.230889Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "odels. Also see the [SynthSAEBench paper](https://arxiv.org/abs/2602.14687) for more details."
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "196a3c7668bcafb79e41f1c4102e884e3682834a43ff0f2eadc49d659b7891f2"
    },
    {
      "model_id": "deepanwa/NuNerZero_onnx",
      "scanned_at": "2026-07-15T02:18:07.984882Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "numind/NuNER_Zero",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:numind/NuNER_Zero"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:numind/NuNER_Zero",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:numind/NuNER_Zero"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "kenizer.json and tokenizer_config.json: Tokenizer vocabulary and configuration files. 6. spm.model: Sen"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gliner",
          "confidence": 0.5,
          "raw_context": "model_type: gliner"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:numind/NuNER_Zero",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "v2.0) dataset, which combines subsets of Pile and C4 annotated via LLMs using [NuNER's procedure](http"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:numind/NuNER_Zero",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2402.15343},       archivePrefix={arXiv},       primaryClass={cs.CL} } ``` ### Previous w"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "voc",
        "arxiv"
      ],
      "base_model": "numind/NuNER_Zero",
      "base_model_chain": [
        "numind/NuNER_Zero"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.35000000000000003,
      "provenance_hash": "8ee4fa5db74d2b566468e7e550c815ad21d270257f5e3f53660ef21232db2037"
    },
    {
      "model_id": "deepdml/whisper-base-ar-mix-norm",
      "scanned_at": "2026-07-15T02:18:12.562067Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "google/fleurs",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:google/fleurs"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "fixie-ai/common_voice_17_0",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:fixie-ai/common_voice_17_0"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "UBC-NLP/Casablanca",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:UBC-NLP/Casablanca"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ymoslem/MediaSpeech",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ymoslem/MediaSpeech"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepdml/Tunisian_MSA",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepdml/Tunisian_MSA"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "openai/whisper-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:openai/whisper-base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:openai/whisper-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:openai/whisper-base"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "openai/whisper-base",
          "confidence": 0.85,
          "raw_context": ": transformers language: - ar license: apache-2.0 base_model: openai/whisper-base tags: - generated_from_trainer datasets: - google"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "openai/whisper-base",
          "confidence": 0.9,
          "raw_context": "_name_or_path: openai/whisper-base"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "whisper",
          "confidence": 0.5,
          "raw_context": "model_type: whisper"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:openai/whisper-base",
          "value": "either English-only data or multilingual",
          "confidence": 0.48,
          "raw_context": "g large-scale weak supervision.   The models were trained on either English-only data or multilingual data. The English-only models were trained  on the tas"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:openai/whisper-base",
          "value": "either English-only or multilingual",
          "confidence": 0.48,
          "raw_context": "ons of varying model sizes. The smallest four are trained on either English-only or multilingual data. The largest checkpoints are multilingual only. A"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:openai/whisper-base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "gnition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)  by Alec Radford et al from O"
        }
      ],
      "declared_datasets": [
        "google/fleurs",
        "ymoslem/MediaSpeech",
        "fixie-ai/common_voice_17_0",
        "UBC-NLP/Casablanca",
        "deepdml/Tunisian_MSA"
      ],
      "inferred_datasets": [
        "either English-only or multilingual",
        "either English-only data or multilingual",
        "arxiv"
      ],
      "base_model": "openai/whisper-base",
      "base_model_chain": [
        "openai/whisper-base"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.95,
      "provenance_hash": "89592715ca2b6c61f412c33f5ff3b962f114e49741779dfb772d37366939560c"
    },
    {
      "model_id": "deepdml/whisper-base-ta-mix-norm",
      "scanned_at": "2026-07-15T02:18:17.334272Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "fixie-ai/common_voice_17_0",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:fixie-ai/common_voice_17_0"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepdml/iisc-mile-tamil-asr",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepdml/iisc-mile-tamil-asr"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepdml/microsoft-speech-corpus-indian",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepdml/microsoft-speech-corpus-indian"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepdml/openslr65-tamil",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepdml/openslr65-tamil"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ai4bharat/Kathbath",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ai4bharat/Kathbath"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "google/fleurs",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:google/fleurs"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "openai/whisper-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:openai/whisper-base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:openai/whisper-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:openai/whisper-base"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "openai/whisper-base",
          "confidence": 0.85,
          "raw_context": ": transformers language: - ta license: apache-2.0 base_model: openai/whisper-base tags: - generated_from_trainer datasets: - fixie-"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "openai/whisper-base",
          "confidence": 0.9,
          "raw_context": "_name_or_path: openai/whisper-base"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "whisper",
          "confidence": 0.5,
          "raw_context": "model_type: whisper"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:openai/whisper-base",
          "value": "either English-only data or multilingual",
          "confidence": 0.48,
          "raw_context": "g large-scale weak supervision.   The models were trained on either English-only data or multilingual data. The English-only models were trained  on the tas"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:openai/whisper-base",
          "value": "either English-only or multilingual",
          "confidence": 0.48,
          "raw_context": "ons of varying model sizes. The smallest four are trained on either English-only or multilingual data. The largest checkpoints are multilingual only. A"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:openai/whisper-base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "gnition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)  by Alec Radford et al from O"
        }
      ],
      "declared_datasets": [
        "deepdml/iisc-mile-tamil-asr",
        "google/fleurs",
        "deepdml/openslr65-tamil",
        "deepdml/microsoft-speech-corpus-indian",
        "fixie-ai/common_voice_17_0",
        "ai4bharat/Kathbath"
      ],
      "inferred_datasets": [
        "either English-only or multilingual",
        "either English-only data or multilingual",
        "arxiv"
      ],
      "base_model": "openai/whisper-base",
      "base_model_chain": [
        "openai/whisper-base"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.95,
      "provenance_hash": "d87bc70bf26c86f80b5bab1eb2d7698363001bfbe89e39034d9a9ec8271a703c"
    },
    {
      "model_id": "deepdml/whisper-large-v3-turbo-af-mix-norm",
      "scanned_at": "2026-07-15T02:18:20.099392Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "voice-biomarkers/openslr-32-hq-SA-languages-Afrikaans",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:voice-biomarkers/openslr-32-hq-SA-languages-Afrikaans"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "andreoosthuizen/afrikaans-30s",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:andreoosthuizen/afrikaans-30s"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "dsfsi-anv/multilingual-nchlt-dataset",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:dsfsi-anv/multilingual-nchlt-dataset"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "google/fleurs",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:google/fleurs"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepdml/whisper-large-v3-turbo",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepdml/whisper-large-v3-turbo"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:deepdml/whisper-large-v3-turbo",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:deepdml/whisper-large-v3-turbo"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "deepdml/whisper-large-v3-turbo",
          "confidence": 0.85,
          "raw_context": "--- language: - af license: apache-2.0 base_model: deepdml/whisper-large-v3-turbo tags: - generated_from_trainer datasets: - voice-"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "deepdml/whisper-large-v3-turbo",
          "confidence": 0.9,
          "raw_context": "_name_or_path: deepdml/whisper-large-v3-turbo"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "whisper",
          "confidence": 0.5,
          "raw_context": "model_type: whisper"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepdml/whisper-large-v3-turbo",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "ibtex @misc{radford2022whisper,   doi = {10.48550/ARXIV.2212.04356},   url = {https://arxiv.org/abs/2212."
        }
      ],
      "declared_datasets": [
        "andreoosthuizen/afrikaans-30s",
        "google/fleurs",
        "dsfsi-anv/multilingual-nchlt-dataset",
        "voice-biomarkers/openslr-32-hq-SA-languages-Afrikaans"
      ],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "deepdml/whisper-large-v3-turbo",
      "base_model_chain": [
        "deepdml/whisper-large-v3-turbo"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.85,
      "provenance_hash": "9cfc999e02de268811e444484308c2bade7df4f17920c52ed10e12677f047333"
    },
    {
      "model_id": "deepdml/whisper-large-v3-turbo-ta-mix-norm",
      "scanned_at": "2026-07-15T02:18:24.704248Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "fixie-ai/common_voice_17_0",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:fixie-ai/common_voice_17_0"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ai4bharat/Kathbath",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ai4bharat/Kathbath"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "google/fleurs",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:google/fleurs"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepdml/microsoft-speech-corpus-indian",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepdml/microsoft-speech-corpus-indian"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepdml/iisc-mile-tamil-asr",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepdml/iisc-mile-tamil-asr"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "openai/whisper-large-v3-turbo",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:openai/whisper-large-v3-turbo"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:openai/whisper-large-v3-turbo",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:openai/whisper-large-v3-turbo"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "openai/whisper-large-v3-turbo",
          "confidence": 0.85,
          "raw_context": "ry_name: transformers language: - ta license: mit base_model: openai/whisper-large-v3-turbo tags: - generated_from_trainer datasets: - fixie-"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "openai/whisper-large-v3-turbo",
          "confidence": 0.9,
          "raw_context": "_name_or_path: openai/whisper-large-v3-turbo"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "whisper",
          "confidence": 0.5,
          "raw_context": "model_type: whisper"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:openai/whisper-large-v3-turbo",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "ibtex @misc{radford2022whisper,   doi = {10.48550/ARXIV.2212.04356},   url = {https://arxiv.org/abs/2212."
        }
      ],
      "declared_datasets": [
        "google/fleurs",
        "deepdml/iisc-mile-tamil-asr",
        "deepdml/microsoft-speech-corpus-indian",
        "fixie-ai/common_voice_17_0",
        "ai4bharat/Kathbath"
      ],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "openai/whisper-large-v3-turbo",
      "base_model_chain": [
        "openai/whisper-large-v3-turbo",
        "openai/whisper-large-v3"
      ],
      "training_section_present": true,
      "license": "mit",
      "provenance_score": 0.85,
      "provenance_hash": "8c0366952d2f7f242cffbf24ed5983378ee95d753b150b1585c0ab0956e66dc5"
    },
    {
      "model_id": "deepdml/whisper-small-ar-mix-norm",
      "scanned_at": "2026-07-15T02:18:30.654654Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "UBC-NLP/Casablanca",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:UBC-NLP/Casablanca"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "fixie-ai/common_voice_17_0",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:fixie-ai/common_voice_17_0"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepdml/Tunisian_MSA",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepdml/Tunisian_MSA"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "google/fleurs",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:google/fleurs"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ymoslem/MediaSpeech",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ymoslem/MediaSpeech"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "openai/whisper-small",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:openai/whisper-small"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:openai/whisper-small",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:openai/whisper-small"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "openai/whisper-small",
          "confidence": 0.85,
          "raw_context": ": transformers language: - ar license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - UBC-NL"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "openai/whisper-small",
          "confidence": 0.9,
          "raw_context": "_name_or_path: openai/whisper-small"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "whisper",
          "confidence": 0.5,
          "raw_context": "model_type: whisper"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:openai/whisper-small",
          "value": "either English-only data or multilingual",
          "confidence": 0.48,
          "raw_context": "g large-scale weak supervision.   The models were trained on either English-only data or multilingual data. The English-only models were trained  on the tas"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:openai/whisper-small",
          "value": "either English-only or multilingual",
          "confidence": 0.48,
          "raw_context": "ons of varying model sizes. The smallest four are trained on either English-only or multilingual data. The largest checkpoints are multilingual only. A"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:openai/whisper-small",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "gnition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)  by Alec Radford et al from O"
        }
      ],
      "declared_datasets": [
        "google/fleurs",
        "ymoslem/MediaSpeech",
        "fixie-ai/common_voice_17_0",
        "UBC-NLP/Casablanca",
        "deepdml/Tunisian_MSA"
      ],
      "inferred_datasets": [
        "either English-only or multilingual",
        "either English-only data or multilingual",
        "arxiv"
      ],
      "base_model": "openai/whisper-small",
      "base_model_chain": [
        "openai/whisper-small"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.95,
      "provenance_hash": "068790c1fcb20313a90cec87f23b7825fa81cc1426ec6d7dd3899bcfd960ae1b"
    },
    {
      "model_id": "deepdml/whisper-tiny-ar-mix-norm",
      "scanned_at": "2026-07-15T02:18:35.237617Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "pain/MASC",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:pain/MASC"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "google/fleurs",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:google/fleurs"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepdml/Tunisian_MSA",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepdml/Tunisian_MSA"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepdml/mtedx",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepdml/mtedx"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "ymoslem/MediaSpeech",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:ymoslem/MediaSpeech"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "UBC-NLP/Casablanca",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:UBC-NLP/Casablanca"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "fixie-ai/common_voice_17_0",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:fixie-ai/common_voice_17_0"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "openai/whisper-tiny",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:openai/whisper-tiny"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:openai/whisper-tiny",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:openai/whisper-tiny"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "openai/whisper-tiny",
          "confidence": 0.85,
          "raw_context": ": transformers language: - ar license: apache-2.0 base_model: openai/whisper-tiny tags: - generated_from_trainer datasets: - pain/M"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "openai/whisper-tiny",
          "confidence": 0.9,
          "raw_context": "_name_or_path: openai/whisper-tiny"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "whisper",
          "confidence": 0.5,
          "raw_context": "model_type: whisper"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:openai/whisper-tiny",
          "value": "either English-only data or multilingual",
          "confidence": 0.48,
          "raw_context": "g large-scale weak supervision.   The models were trained on either English-only data or multilingual data. The English-only models were trained  on the tas"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:openai/whisper-tiny",
          "value": "either English-only or multilingual",
          "confidence": 0.48,
          "raw_context": "ons of varying model sizes. The smallest four are trained on either English-only or multilingual data. The largest checkpoints are multilingual only. A"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:openai/whisper-tiny",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "gnition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)  by Alec Radford et al from O"
        }
      ],
      "declared_datasets": [
        "google/fleurs",
        "pain/MASC",
        "ymoslem/MediaSpeech",
        "fixie-ai/common_voice_17_0",
        "UBC-NLP/Casablanca",
        "deepdml/Tunisian_MSA",
        "deepdml/mtedx"
      ],
      "inferred_datasets": [
        "either English-only or multilingual",
        "either English-only data or multilingual",
        "arxiv"
      ],
      "base_model": "openai/whisper-tiny",
      "base_model_chain": [
        "openai/whisper-tiny"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.95,
      "provenance_hash": "80ae28caf395f466f9345837eb717b96de1679fce034e22b720ad581e316045e"
    },
    {
      "model_id": "deepmind/language-perceiver",
      "scanned_at": "2026-07-15T02:18:39.821410Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "wikipedia",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:wikipedia"
        },
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "c4",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:c4"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.6,
          "raw_context": "-- language: - en license: apache-2.0 datasets: - wikipedia - c4 inference: false ---  # Perceiver IO for lan"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "modeling head, of shape (batch_size, seq_length, vocab_size).  <img src=\"https://huggingface.co/datase"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "- en license: apache-2.0 datasets: - wikipedia - c4 inference: false ---  # Perceiver IO for language"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "glue",
          "confidence": 0.7,
          "raw_context": "el is able to achieve an average score of 81.8 on GLUE. For more details, we refer to table 3 of the ori"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ge Modeling (MLM) task proposed in [BERT](https://arxiv.org/abs/1810.04805) using a large text corpus obt"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.7,
          "raw_context": "-- language: - en license: apache-2.0 datasets: - wikipedia - c4 inference: false ---  # Perceiver IO for lan"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "perceiver",
          "confidence": 0.5,
          "raw_context": "model_type: perceiver"
        }
      ],
      "declared_datasets": [
        "c4",
        "wikipedia"
      ],
      "inferred_datasets": [
        "c4",
        "glue",
        "wikipedia",
        "voc",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.8,
      "provenance_hash": "c09df95925752abc80d2a6d937d7bb5dd4fc7cced24961a3bdbcb8de1339579c"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Coder-V2-Base",
      "scanned_at": "2026-07-15T02:18:42.572144Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "36B parameters based on the [DeepSeekMoE](https://arxiv.org/pdf/2401.06066) framework, which has actived"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "deaec27b2c80931ddc9f4bba206b451aa125efe37775167f4425d5d4cd4fba71"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Coder-V2-Instruct",
      "scanned_at": "2026-07-15T02:18:45.348255Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepseek-ai/DeepSeek-Coder-V2-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepseek-ai/DeepSeek-Coder-V2-Base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:deepseek-ai/DeepSeek-Coder-V2-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:deepseek-ai/DeepSeek-Coder-V2-Base"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "deepseek-ai/DeepSeek-Coder-V2-Base",
          "confidence": 0.85,
          "raw_context": "ense_name: deepseek-license license_link: LICENSE base_model: deepseek-ai/DeepSeek-Coder-V2-Base --- <!-- markdownlint-disable first-line-h1 --> <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "36B parameters based on the [DeepSeekMoE](https://arxiv.org/pdf/2401.06066) framework, which has actived"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-Coder-V2-Base",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-Coder-V2-Base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "36B parameters based on the [DeepSeekMoE](https://arxiv.org/pdf/2401.06066) framework, which has actived"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "deepseek-ai/DeepSeek-Coder-V2-Base",
      "base_model_chain": [
        "deepseek-ai/DeepSeek-Coder-V2-Base"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "4bd9fbe48fde923ea63598c391b01fcc056cff48902c8b5767796056d1d7c656"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Coder-V2-Lite-Base",
      "scanned_at": "2026-07-15T02:18:48.104551Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "36B parameters based on the [DeepSeekMoE](https://arxiv.org/pdf/2401.06066) framework, which has actived"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "43f629ae4507e78f26b7b667de2f4cdffac4e714ddef64deeb92a064097081a3"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Math-V2",
      "scanned_at": "2026-07-15T02:18:50.862287Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepseek-ai/DeepSeek-Math-V2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepseek-ai/DeepSeek-Math-V2"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:deepseek-ai/DeepSeek-Math-V2",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:deepseek-ai/DeepSeek-Math-V2"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "te\"/></a>   <br>   <a href=\"https://discord.gg/Tc7c45Zzu5\"><img alt=\"Discord\"     src=\"https://img.shi"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v32",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v32"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "d458cbe45671e3e9820c305f9c012fd01a874dca2775717ff8bf70b2136bf5e0"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Prover-V1",
      "scanned_at": "2026-07-15T02:18:53.617587Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "/a> </p>    <p align=\"center\">   <a href=\"https://arxiv.org/abs/2405.14333\"><b>Paper Link</b>👁️</a> </p>"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "18158ecd6774ef0d5d384c1296f5b8d9365c3d1046dde1297a761dbe9d01fe93"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Prover-V1.5-Base",
      "scanned_at": "2026-07-15T02:18:56.363780Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "/a> </p>    <p align=\"center\">   <a href=\"https://arxiv.org/abs/2408.08152\"><b>Paper Link</b>👁️</a> </p>"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "e615b6e0a81792ee23ec9512612b3f864140d42f520ea506277c109b11739cd4"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Prover-V1.5-RL",
      "scanned_at": "2026-07-15T02:18:59.137768Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepseek-ai/DeepSeek-Prover-V1.5-SFT",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepseek-ai/DeepSeek-Prover-V1.5-SFT"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:deepseek-ai/DeepSeek-Prover-V1.5-SFT",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:deepseek-ai/DeepSeek-Prover-V1.5-SFT"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "deepseek-ai/DeepSeek-Prover-V1.5-SFT",
          "confidence": 0.85,
          "raw_context": "ense_name: deepseek-license license_link: LICENSE base_model: deepseek-ai/DeepSeek-Prover-V1.5-SFT --- <!-- markdownlint-disable first-line-h1 --> <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "/a> </p>    <p align=\"center\">   <a href=\"https://arxiv.org/abs/2408.08152\"><b>Paper Link</b>👁️</a> </p>"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-Prover-V1.5-SFT",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-Prover-V1.5-SFT",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "/a> </p>    <p align=\"center\">   <a href=\"https://arxiv.org/abs/2408.08152\"><b>Paper Link</b>👁️</a> </p>"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "deepseek-ai/DeepSeek-Prover-V1.5-SFT",
      "base_model_chain": [
        "deepseek-ai/DeepSeek-Prover-V1.5-SFT",
        "deepseek-ai/DeepSeek-Prover-V1.5-Base"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "f49625b6343ff0b440e87a49ab35218f8665b354599967a202de0827903a5bb1"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Prover-V1.5-SFT",
      "scanned_at": "2026-07-15T02:19:03.710561Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepseek-ai/DeepSeek-Prover-V1.5-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepseek-ai/DeepSeek-Prover-V1.5-Base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:deepseek-ai/DeepSeek-Prover-V1.5-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:deepseek-ai/DeepSeek-Prover-V1.5-Base"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "deepseek-ai/DeepSeek-Prover-V1.5-Base",
          "confidence": 0.85,
          "raw_context": "ense_name: deepseek-license license_link: LICENSE base_model: deepseek-ai/DeepSeek-Prover-V1.5-Base --- <!-- markdownlint-disable first-line-h1 --> <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "/a> </p>    <p align=\"center\">   <a href=\"https://arxiv.org/abs/2408.08152\"><b>Paper Link</b>👁️</a> </p>"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-Prover-V1.5-Base",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-Prover-V1.5-Base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "/a> </p>    <p align=\"center\">   <a href=\"https://arxiv.org/abs/2408.08152\"><b>Paper Link</b>👁️</a> </p>"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "deepseek-ai/DeepSeek-Prover-V1.5-Base",
      "base_model_chain": [
        "deepseek-ai/DeepSeek-Prover-V1.5-Base"
      ],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "92d72ce612db5c0a61ccda865c5c772eb48889bcf9a6030ef624687fe75dd5af"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Prover-V2-671B",
      "scanned_at": "2026-07-15T02:19:04.639430Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v3",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v3"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "2c4f009ba96ac705460827d6fd6aa271a309f8c133a34b40db302995cc329003"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-Prover-V2-7B",
      "scanned_at": "2026-07-15T02:19:07.387770Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "c939695cfc603c9ee446412d208ae8e79dd6786649aa927685aca71025740cef"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-R1-Zero",
      "scanned_at": "2026-07-15T02:19:10.179675Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "| 72.5 | 80.5 | 73.3 | 76.9 | - | **82.5** | | | AlpacaEval2.0 (LC-winrate) | 52.0 | 51.1 | 70.0 | 57.8 |"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": ",       eprint={2501.12948},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v3",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v3"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "alpaca",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.25,
      "provenance_hash": "5f58dd2435d4801ce919e7176b11a1ef5d5294e42060fadc0c1e6f2f9b8dc535"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-V2",
      "scanned_at": "2026-07-15T02:19:12.927707Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "ed Generation Evaluation We evaluate our model on AlpacaEval 2.0 and MTBench, showing the competitive perf"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ded Generation Evaluation **Alignbench** (https://arxiv.org/abs/2311.18743) <div align=\"center\">  | **模型*"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "alpaca",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.25,
      "provenance_hash": "a16d9c4520662e0897a55479757b28751c62e11c756a93b876644321521444b2"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-V2-Chat",
      "scanned_at": "2026-07-15T02:19:15.715742Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "ed Generation Evaluation We evaluate our model on AlpacaEval 2.0 and MTBench, showing the competitive perf"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "n</a> </p>  <p align=\"center\">   <a href=\"https://arxiv.org/abs/2405.04434\"><b>Paper Link</b>👁️</a> </p>"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "alpaca",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.25,
      "provenance_hash": "cbe3b1d31d9ec4caefe6df1b283b98e070e2bd058ee31baffb827f0557a326e2"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-V2-Chat-0628",
      "scanned_at": "2026-07-15T02:19:18.470812Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ne-height: 1;\">\r   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": ">\r </p>\r \r <p align=\"center\">\r   <a href=\"https://arxiv.org/abs/2405.04434\"><b>Paper Link</b>👁️</a>\r </p>"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "b03074c0e427f783f785aa4474da7880c5e8c937d2dfcf30aef91f80d737ee33"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-V2.5",
      "scanned_at": "2026-07-15T02:19:21.233000Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "alpaca",
          "confidence": 0.7,
          "raw_context": "-----|:-----------------------|:--------------| | AlpacaEval 2.0          | 46.6             | 44.5"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "/a> </div>  <p align=\"center\">   <a href=\"https://arxiv.org/abs/2405.04434\"><b>Paper Link</b>👁️</a> </p>"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "alpaca",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.25,
      "provenance_hash": "07fd444ff0401b46067ffff3172e5118299b0ab946ff8177bbd173b3f3b90678"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-V2.5-1210",
      "scanned_at": "2026-07-15T02:19:24.036486Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "/a> </div>  <p align=\"center\">   <a href=\"https://arxiv.org/abs/2405.04434\"><b>Paper Link</b>👁️</a> </p>"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "6aa811e0349f227fe3afab592e8cfc14b17e680b2f141b641c8281c37c062bb7"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-V3.1-Base",
      "scanned_at": "2026-07-15T02:19:26.822525Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": ",       eprint={2412.19437},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v3",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v3"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.2,
      "provenance_hash": "65339271f6306ebfaf30ce9c47924fa837ffbbba6260f37b767527786a31f17c"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-V3.1-Terminus",
      "scanned_at": "2026-07-15T02:19:29.574731Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepseek-ai/DeepSeek-V3.1-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepseek-ai/DeepSeek-V3.1-Base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:deepseek-ai/DeepSeek-V3.1-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:deepseek-ai/DeepSeek-V3.1-Base"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": ",       eprint={2412.19437},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v3",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v3"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-V3.1-Base",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepseek-ai/DeepSeek-V3.1-Base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2412.19437},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "deepseek-ai/DeepSeek-V3.1-Base",
      "base_model_chain": [
        "deepseek-ai/DeepSeek-V3.1-Base"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "8e063e4213804b360cefc64fc662a073320937f6db21981373c796cd4e0bec2a"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-V3.2-Exp",
      "scanned_at": "2026-07-15T02:19:32.341867Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepseek-ai/DeepSeek-V3.2-Exp-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepseek-ai/DeepSeek-V3.2-Exp-Base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:deepseek-ai/DeepSeek-V3.2-Exp-Base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:deepseek-ai/DeepSeek-V3.2-Exp-Base"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "ine-height: 1;\">   <a href=\"https://discord.gg/Tc7c45Zzu5\" target=\"_blank\" style=\"margin: 2px;\">     <"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v32",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v32"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": "deepseek-ai/DeepSeek-V3.2-Exp-Base",
      "base_model_chain": [
        "deepseek-ai/DeepSeek-V3.2-Exp-Base"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.25,
      "provenance_hash": "6e6f75cf3f04a00d290733e6c862dd06871d37c0c21ff71349b54bded5170beb"
    },
    {
      "model_id": "deepseek-ai/DeepSeek-V3.2-Exp-Base",
      "scanned_at": "2026-07-15T02:19:35.998554Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v32",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v32"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.1,
      "provenance_hash": "2df7480bdfad10ff657e053e1fbc2d05ff65737f089ab68ce8280bf63a041653"
    },
    {
      "model_id": "deepseek-ai/ESFT-gate-code-lite",
      "scanned_at": "2026-07-15T02:19:36.918761Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "eee2936fbfbecc8db661ba274ae0c60587097149178e27ee703c9449dfadefee"
    },
    {
      "model_id": "deepseek-ai/ESFT-gate-intent-lite",
      "scanned_at": "2026-07-15T02:19:39.669129Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "0218c0ea3cea20ddee37c4af2fde8ddc5be5abf8b8dd981e6c4fdbf783967ee8"
    },
    {
      "model_id": "deepseek-ai/ESFT-gate-law-lite",
      "scanned_at": "2026-07-15T02:19:42.423497Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "e7e1c3618b7d2a65ecc88019debba05e26d3a10d16228743901de6659418069a"
    },
    {
      "model_id": "deepseek-ai/ESFT-gate-math-lite",
      "scanned_at": "2026-07-15T02:19:45.170825Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "e424342058a7dac2d0e9489298b62152a747ac1e49606ca67d0fff59cc9810f6"
    },
    {
      "model_id": "deepseek-ai/ESFT-gate-summary-lite",
      "scanned_at": "2026-07-15T02:19:47.917794Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "9e1149f2fac771171c507b006abe77d1e1245852ae3f5da1d9e41ce84fe9c26a"
    },
    {
      "model_id": "deepseek-ai/ESFT-gate-translation-lite",
      "scanned_at": "2026-07-15T02:19:50.733442Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "749aa2887bef6da9babe35683391a64715892d64e83d1b3c3c56eaef16d5beb2"
    },
    {
      "model_id": "deepseek-ai/ESFT-token-code-lite",
      "scanned_at": "2026-07-15T02:19:53.479205Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "124907b1eba6ef96c4a935344b008f11472a07c79b2557776c3bf829c9182f70"
    },
    {
      "model_id": "deepseek-ai/ESFT-token-intent-lite",
      "scanned_at": "2026-07-15T02:19:56.227518Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "7a77e7e9b64545d2ef332d2a79195a096813af907ac8a7fb544ba8dbeccc8d99"
    },
    {
      "model_id": "deepseek-ai/ESFT-token-law-lite",
      "scanned_at": "2026-07-15T02:19:58.998816Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "62f3bf8c368dcaa489329919201ef3be7328ef48f500aaf5b23da5a6cb0ef473"
    },
    {
      "model_id": "deepseek-ai/ESFT-token-math-lite",
      "scanned_at": "2026-07-15T02:20:01.745567Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "029522bad5a8ac7e626af1a581a179bd3a2e058f6896ddac36195f1a5a0408ba"
    },
    {
      "model_id": "deepseek-ai/ESFT-token-summary-lite",
      "scanned_at": "2026-07-15T02:20:04.485526Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "5bca05656f56f8ded56ca1fc37928a9e350264b4af8360c288f6532006e5e831"
    },
    {
      "model_id": "deepseek-ai/ESFT-token-translation-lite",
      "scanned_at": "2026-07-15T02:20:07.326070Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "f8a2a2858ae81b3a5df2e020868ee0d3f579af095bf98a7c464b42d3ba009d40"
    },
    {
      "model_id": "deepseek-ai/ESFT-vanilla-lite",
      "scanned_at": "2026-07-15T02:20:10.255236Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "alized Fine-Tuning (ESFT) research paper: https://arxiv.org/abs/2407.01906.  To use this model and specia"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "1d7dad152a42cc1ca95ff35a275a93d5acd3a98d7250f006971ad7c169a4b4ab"
    },
    {
      "model_id": "deepseek-ai/Janus-1.3B",
      "scanned_at": "2026-07-15T02:20:12.996521Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "an approximate",
          "confidence": 0.6,
          "raw_context": "cted based on the DeepSeek-LLM-1.3b-base which is trained on an approximate corpus of 500B text tokens. For multimodal understanding"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Multimodal Understanding and Generation](https://arxiv.org/abs/2410.13848)  [**Github Repository**](http"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "multi_modality",
          "confidence": 0.5,
          "raw_context": "model_type: multi_modality"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "e554fdc6d71123c8de1a2d6bfef5a88309b09da1e1981a0c5739b36a3a716916"
    },
    {
      "model_id": "deepseek-ai/Janus-Pro-1B",
      "scanned_at": "2026-07-15T02:20:15.739045Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "enda and Yu, Xingkai and Ruan, Chong},   journal={arXiv preprint arXiv:2501.17811},   year={2025} } ```"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "multi_modality",
          "confidence": 0.5,
          "raw_context": "model_type: multi_modality"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "6079f446a4b8132474ac1fa3d9afae9ce692975234d4e82da148930b817f1bdd"
    },
    {
      "model_id": "deepseek-ai/JanusFlow-1.3B",
      "scanned_at": "2026-07-15T02:20:18.600589Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Multimodal Understanding and Generation](https://arxiv.org/abs/2411.07975)  [**Github Repository**](http"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "multi_modality",
          "confidence": 0.5,
          "raw_context": "model_type: multi_modality"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "ade699095046ad9a492a9efb2c84b314216ca42a22fe1e7c02f0dfe31d99c9c3"
    },
    {
      "model_id": "deepseek-ai/deepseek-coder-1.3b-base",
      "scanned_at": "2026-07-15T02:20:21.370947Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "project-level code",
          "confidence": 0.6,
          "raw_context": "l, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fil"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "eek Coder]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "e86c492603778c3002e7e793a9762c97b08caed17f9e1c7d702ad229fd9d16bb"
    },
    {
      "model_id": "deepseek-ai/deepseek-coder-33b-base",
      "scanned_at": "2026-07-15T02:20:24.123565Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "project-level code",
          "confidence": 0.6,
          "raw_context": "l, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fil"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "eek Coder]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "b3e6749a2dd971ed99c0b7d9910770a32ad1c8b3b6744fc1e3630a82063bcf91"
    },
    {
      "model_id": "deepseek-ai/deepseek-coder-33b-instruct",
      "scanned_at": "2026-07-15T02:20:26.869780Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "project-level code",
          "confidence": 0.6,
          "raw_context": "l, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fil"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "eek Coder]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "52ce6844baea7f74df5719ba52a4baed47dafb772c56a4fe88ddfaa7aeab1c27"
    },
    {
      "model_id": "deepseek-ai/deepseek-coder-5.7bmqa-base",
      "scanned_at": "2026-07-15T02:20:29.635507Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "project-level code",
          "confidence": 0.6,
          "raw_context": "l, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fil"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "eek Coder]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "e4323bb740e9e7f8e4641f908caac349933105142e53be0cc3026e4a7536710d"
    },
    {
      "model_id": "deepseek-ai/deepseek-coder-6.7b-base",
      "scanned_at": "2026-07-15T02:20:32.377276Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "project-level code",
          "confidence": 0.6,
          "raw_context": "l, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fil"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "eek Coder]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "67fad178e75fc8ef71f631d49c2e051b9f393854fe04cc47c1eb15121f64253a"
    },
    {
      "model_id": "deepseek-ai/deepseek-coder-6.7b-instruct",
      "scanned_at": "2026-07-15T02:20:35.124672Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "project-level code",
          "confidence": 0.6,
          "raw_context": "l, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fil"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "eek Coder]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "/3fs-jd/prod/deepseek/shared/zhuqihao/public_model/deepseek-coder-7b-instruct2",
          "confidence": 0.9,
          "raw_context": "_name_or_path: /3fs-jd/prod/deepseek/shared/zhuqihao/public_model/deepseek-coder-7b-instruct2"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "90dd81246d36b1b64b4d6487be58986b5851688b8ef3f5d92d90f207eb67a2f5"
    },
    {
      "model_id": "deepseek-ai/deepseek-coder-7b-base-v1.5",
      "scanned_at": "2026-07-15T02:20:37.872048Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "eek Coder]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "f27002941bb85539d85485105512ad9e6e89626e74f6049f914f99b6633f51bc"
    },
    {
      "model_id": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
      "scanned_at": "2026-07-15T02:20:40.618653Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "eek Coder]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "bffd8b93a02cbb29b452844fb274a109e6bdfdfc9584792a6e1df0cda12ff1a3"
    },
    {
      "model_id": "deepseek-ai/deepseek-llm-67b-base",
      "scanned_at": "2026-07-15T02:20:43.357410Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "pSeek LLM]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "6b74bc8f98bf73384c8c20225aa7c2126aa8c251e0cb3a724c7a0a77779a268a"
    },
    {
      "model_id": "deepseek-ai/deepseek-llm-67b-chat",
      "scanned_at": "2026-07-15T02:20:46.106986Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "extra instruction",
          "confidence": 0.6,
          "raw_context": "odel initialized from `deepseek-llm-67b-base` and fine-tuned on extra instruction data. - **Home Page:** [DeepSeek](https://deepseek.com"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "pSeek LLM]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "48edd74dda932e9b6f0cc3cf0d032b709e7c0ac1196eb288497c183229040d86"
    },
    {
      "model_id": "deepseek-ai/deepseek-llm-7b-base",
      "scanned_at": "2026-07-15T02:20:48.847054Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "pSeek LLM]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "3aa31f9ee6c9190b0bf6677b510f145678d813604a1dda99b5f35c3c5d52ef33"
    },
    {
      "model_id": "deepseek-ai/deepseek-llm-7b-chat",
      "scanned_at": "2026-07-15T02:20:51.629706Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "extra instruction",
          "confidence": 0.6,
          "raw_context": "model initialized from `deepseek-llm-7b-base` and fine-tuned on extra instruction data.  - **Home Page:** [DeepSeek](https://deepseek.co"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "pSeek LLM]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "01cbf43a427f570ee35cff04091b533cb1e7422b41b8579be5a6104bc37b06c2"
    },
    {
      "model_id": "deepseek-ai/deepseek-math-7b-base",
      "scanned_at": "2026-07-15T02:20:54.395041Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "pSeek LLM]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "]</a> </p>  <p align=\"center\">   <a href=\"https://arxiv.org/pdf/2402.03300.pdf\"><b>Paper Link</b>👁️</a> <"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "de4b74bb3628663d626ae9beb3134acf4bc65c7e2a6f00ca92ba1dd44548816f"
    },
    {
      "model_id": "deepseek-ai/deepseek-math-7b-instruct",
      "scanned_at": "2026-07-15T02:20:57.141363Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "pSeek LLM]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "]</a> </p>  <p align=\"center\">   <a href=\"https://arxiv.org/pdf/2402.03300.pdf\"><b>Paper Link</b>👁️</a> <"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "a265c80267e0695078e1036ba0f91aa26f6db31f2b22c9d551832be23801418c"
    },
    {
      "model_id": "deepseek-ai/deepseek-math-7b-rl",
      "scanned_at": "2026-07-15T02:20:59.881763Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "pSeek LLM]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "]</a> </p>  <p align=\"center\">   <a href=\"https://arxiv.org/pdf/2402.03300.pdf\"><b>Paper Link</b>👁️</a> <"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "a3dae58c77d9c9745883d3451bc80ff910b6ab155a846b9a3c8b510b67e051ee"
    },
    {
      "model_id": "deepseek-ai/deepseek-moe-16b-base",
      "scanned_at": "2026-07-15T02:21:02.763978Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "pSeek LLM]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "]</a> </p>  <p align=\"center\">   <a href=\"https://arxiv.org/pdf/2401.06066.pdf\"><b>Paper Link</b>👁️</a> <"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "1060dbf51e8d3cdc66fd0c26be8e535f9ae83f122f4a2034fb9880d3d4086b9a"
    },
    {
      "model_id": "deepseek-ai/deepseek-moe-16b-chat",
      "scanned_at": "2026-07-15T02:21:05.503314Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "pSeek LLM]</a>  |  <a href=\"https://discord.gg/Tc7c45Zzu5\">[Discord]</a>  |  <a href=\"https://github.c"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "]</a> </p>  <p align=\"center\">   <a href=\"https://arxiv.org/pdf/2401.06066.pdf\"><b>Paper Link</b>👁️</a> <"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.2,
      "provenance_hash": "847fe0271e065ad806d57158f05effd05cd313ca42eb2537ee2f646ff1412c38"
    },
    {
      "model_id": "deepseek-ai/deepseek-vl-1.3b-base",
      "scanned_at": "2026-07-15T02:21:08.252273Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "an approximate",
          "confidence": 0.6,
          "raw_context": "cted based on the DeepSeek-LLM-1.3b-base which is trained on an approximate corpus of 500B text tokens. The whole DeepSeek-VL-1.3b-b"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Real-World Vision-Language Understanding](https://arxiv.org/abs/2403.05525)  [**Github Repository**](http"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "multi_modality",
          "confidence": 0.5,
          "raw_context": "model_type: multi_modality"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "456d17bec9920ac4581507dd2dd9c3880016397539f69a1759d440e1d7f6d99b"
    },
    {
      "model_id": "deepseek-ai/deepseek-vl-1.3b-chat",
      "scanned_at": "2026-07-15T02:21:10.996407Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "an approximate",
          "confidence": 0.6,
          "raw_context": "cted based on the DeepSeek-LLM-1.3b-base which is trained on an approximate corpus of 500B text tokens. The whole DeepSeek-VL-1.3b-b"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Real-World Vision-Language Understanding](https://arxiv.org/abs/2403.05525)  [**Github Repository**](http"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "multi_modality",
          "confidence": 0.5,
          "raw_context": "model_type: multi_modality"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "fec070d1fbc1b26bf5778f8a4cff24eab5e2f5fe190dcf9622133cd145d8818e"
    },
    {
      "model_id": "deepseek-ai/deepseek-vl-7b-base",
      "scanned_at": "2026-07-15T02:21:13.886978Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "an approximate",
          "confidence": 0.6,
          "raw_context": "ructed based on the DeepSeek-LLM-7b-base which is trained on an approximate corpus of 2T text tokens. The whole DeepSeek-VL-7b-base"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Real-World Vision-Language Understanding](https://arxiv.org/abs/2403.05525)  [**Github Repository**](http"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "multi_modality",
          "confidence": 0.5,
          "raw_context": "model_type: multi_modality"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "8a97a18610f48084fb44e6769da144678117c512905dae664a386aff24c9e86d"
    },
    {
      "model_id": "deepseek-ai/deepseek-vl-7b-chat",
      "scanned_at": "2026-07-15T02:21:16.742098Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "an approximate",
          "confidence": 0.6,
          "raw_context": "ructed based on the DeepSeek-LLM-7b-base which is trained on an approximate corpus of 2T text tokens. The whole DeepSeek-VL-7b-base"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "Real-World Vision-Language Understanding](https://arxiv.org/abs/2403.05525)  [**Github Repository**](http"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "multi_modality",
          "confidence": 0.5,
          "raw_context": "model_type: multi_modality"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "8256ecd1ed005ea48937193f15424d85b58e0e647d34aaab893617088cdaa2f9"
    },
    {
      "model_id": "deepseek-ai/deepseek-vl2",
      "scanned_at": "2026-07-15T02:21:19.493420Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ls for Advanced Multimodal Understanding](https://arxiv.org/abs/2412.10302)  [**Github Repository**](http"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "deepseek_vl_v2",
          "confidence": 0.5,
          "raw_context": "model_type: deepseek_vl_v2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "9f1661162fa57bdcc646ffbff069cdf0787943ad5977686e1259f71f8dfce09b"
    },
    {
      "model_id": "deepvk/GeRaCl-USER2-base",
      "scanned_at": "2026-07-15T02:21:22.246138Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "deepvk/GeRaCl_synthethic_dataset",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:deepvk/GeRaCl_synthethic_dataset"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "deepvk/USER2-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:deepvk/USER2-base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:deepvk/USER2-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:deepvk/USER2-base"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "GeRaCl_synthethic_dataset/synthetic_classes_train",
          "confidence": 0.8,
          "raw_context": "amples | |----------------------------:|:----:| | [GeRaCl_synthethic_dataset/synthetic_classes_train](https://huggingface.co/datasets/deepvk/GeRaCl_synthethic_dataset/viewer/synthetic_"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "GeRaCl_synthethic_dataset/ru_mteb_classes",
          "confidence": 0.8,
          "raw_context": "hetic_classes_train)                    | 99K | | [GeRaCl_synthethic_dataset/ru_mteb_classes](https://huggingface.co/datasets/deepvk/GeRaCl_synthethic_dataset/viewer/ru_mteb_cl"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "GeRaCl_synthethic_dataset/ru_mteb_extended_classes",
          "confidence": 0.8,
          "raw_context": "r/ru_mteb_classes/)                    | 52K  | | [GeRaCl_synthethic_dataset/ru_mteb_extended_classes](https://huggingface.co/datasets/deepvk/GeRaCl_synthethic_dataset/viewer/ru_mteb_ex"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "GeRaCl",
          "confidence": 0.5,
          "raw_context": "model_type: GeRaCl"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "cultura-sampled",
          "confidence": 0.48,
          "raw_context": "En-Ru parallel              | 250M |   1      | | [cultura-sampled](https://huggingface.co/datasets/deepvk/cultura_ru_edu)             | 50M  |   1"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "Nomic-en-supervised",
          "confidence": 0.48,
          "raw_context": "-:|:------------------------------------------| | [Nomic-en-supervised](https://huggingface.co/datasets/nomic-ai/nomic-embed-supervised-data)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "fishkinet-posts",
          "confidence": 0.48,
          "raw_context": "| Translated SNLI/MNLI/ANLI to Russian      | | [fishkinet-posts](https://huggingface.co/datasets/nyuuzyou/fishkinet-posts)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "gazeta",
          "confidence": 0.48,
          "raw_context": "| Title–content pairs                       | | [gazeta](https://huggingface.co/datasets/IlyaGusev/gazeta)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "habr_qna",
          "confidence": 0.48,
          "raw_context": "| Title–text pairs                          | | [habr_qna](https://huggingface.co/datasets/its5Q/habr_qna)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "lenta",
          "confidence": 0.48,
          "raw_context": "| Title–description pairs                   | | [lenta](https://huggingface.co/datasets/zloelias/lenta-ru)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "miracl_ru",
          "confidence": 0.48,
          "raw_context": "| Title–news pairs                          | | [miracl_ru](https://huggingface.co/datasets/Shitao/bge-m3-data)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "mldr_ru",
          "confidence": 0.48,
          "raw_context": "| One positive per anchor                   | | [mldr_ru](https://huggingface.co/datasets/Shitao/bge-m3-data)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "mr-tydi_ru",
          "confidence": 0.48,
          "raw_context": "| Unmodified                                | | [mr-tydi_ru](https://huggingface.co/datasets/Shitao/bge-m3-data)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "mmarco_ru",
          "confidence": 0.48,
          "raw_context": "| Unmodified                                | | [mmarco_ru](https://huggingface.co/datasets/unicamp-dl/mmarco)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "ru-HNP",
          "confidence": 0.48,
          "raw_context": "| 500 K    | Unmodified                       | | [ru-HNP](https://huggingface.co/datasets/deepvk/ru-HNP)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "sampled_wiki",
          "confidence": 0.48,
          "raw_context": "tailment -> pos, contradiction -> neg         | | [sampled_wiki](https://huggingface.co/datasets/wikimedia/wikipedia)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "summ_dialog_news",
          "confidence": 0.48,
          "raw_context": "| Sampled text blocks from Wikipedia        | | [summ_dialog_news](https://huggingface.co/datasets/CarlBrendt/Summ_Dialog_News)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "wikiomnia_qna",
          "confidence": 0.48,
          "raw_context": "| Summary–info pairs                        | | [wikiomnia_qna](https://huggingface.co/datasets/RussianNLP/wikiomnia)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "yandex_q",
          "confidence": 0.48,
          "raw_context": "| QA pairs (T5-generated)                  | | [yandex_q](https://huggingface.co/datasets/its5Q/yandex-q)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "wikipedia",
          "confidence": 0.48,
          "raw_context": "s - IlyaGusev/gazeta - its5Q/habr_qna - wikimedia/wikipedia - RussianNLP/wikiomnia language: - ru ---  # USER"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "Matryoshka Representation Learning (MRL)](https://arxiv.org/abs/2205.13147) — a technique that enables re"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:deepvk/USER2-base",
          "value": "wikipedia",
          "confidence": 0.5599999999999999,
          "raw_context": "s - IlyaGusev/gazeta - its5Q/habr_qna - wikimedia/wikipedia - RussianNLP/wikiomnia language: - ru ---  # USER"
        }
      ],
      "declared_datasets": [
        "GeRaCl_synthethic_dataset/ru_mteb_classes",
        "deepvk/GeRaCl_synthethic_dataset",
        "GeRaCl_synthethic_dataset/synthetic_classes_train",
        "GeRaCl_synthethic_dataset/ru_mteb_extended_classes"
      ],
      "inferred_datasets": [
        "cultura-sampled",
        "habr_qna",
        "yandex_q",
        "ru-HNP",
        "mldr_ru",
        "wikipedia",
        "lenta",
        "mmarco_ru",
        "wikiomnia_qna",
        "Nomic-en-supervised",
        "miracl_ru",
        "sampled_wiki",
        "arxiv",
        "fishkinet-posts",
        "gazeta",
        "summ_dialog_news",
        "mr-tydi_ru"
      ],
      "base_model": "deepvk/USER2-base",
      "base_model_chain": [
        "deepvk/USER2-base",
        "deepvk/RuModernBERT-base"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 1.0,
      "provenance_hash": "1781881a8dca7d1790e47dd9acd06f1ade1d4928154b815875730f5aa277ace8"
    },
    {
      "model_id": "dell-research-harvard/lt-wikidata-comp-multi",
      "scanned_at": "2026-07-15T02:21:27.782162Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "nt={2309.00789},                   archivePrefix={arXiv},                   primaryClass={cs.CL}"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
          "confidence": 0.9,
          "raw_context": "_name_or_path: sentence-transformers/paraphrase-multilingual-mpnet-base-v2"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "xlm-roberta",
          "confidence": 0.5,
          "raw_context": "model_type: xlm-roberta"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.35,
      "provenance_hash": "77dda17f75ccaadb189158725758e7210eb2f276163966fda829ab6518ee0180"
    },
    {
      "model_id": "depth-anything/DA3-GIANT-1.1",
      "scanned_at": "2026-07-15T02:21:30.535860Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "academic",
          "confidence": 0.6,
          "raw_context": "o).  # noqa: E501  ## Limitations  - The model is trained on academic datasets and may have limitations on certain domain-speci"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "github.io) [![Paper](https://img.shields.io/badge/arXiv-Depth_Anything_3-red)](https://arxiv.org/abs/) [!"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "cc-by-nc-4.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "5886f48acbd66f47486e6effa21fd7f2f31d3da0d3420d04592c68474098cfcc"
    },
    {
      "model_id": "depth-anything/DA3-LARGE",
      "scanned_at": "2026-07-15T02:21:33.283033Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "academic",
          "confidence": 0.6,
          "raw_context": "o).  # noqa: E501  ## Limitations  - The model is trained on academic datasets and may have limitations on certain domain-speci"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "github.io) [![Paper](https://img.shields.io/badge/arXiv-Depth_Anything_3-red)](https://arxiv.org/abs/) [!"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "cc-by-nc-4.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "ea7f0d19ce6e47a0b89f21289eba129642a8b1416e43df31518a4c2495369150"
    },
    {
      "model_id": "depth-anything/DA3-LARGE-1.1",
      "scanned_at": "2026-07-15T02:21:36.031285Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "academic",
          "confidence": 0.6,
          "raw_context": "o).  # noqa: E501  ## Limitations  - The model is trained on academic datasets and may have limitations on certain domain-speci"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "github.io) [![Paper](https://img.shields.io/badge/arXiv-Depth_Anything_3-red)](https://arxiv.org/abs/) [!"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "bed0353ea79f2472db8d3e3d78918d3257fbe516ee86c46c46d1376fffd1c585"
    },
    {
      "model_id": "depth-anything/DA3-SMALL",
      "scanned_at": "2026-07-15T02:21:38.773472Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "academic",
          "confidence": 0.6,
          "raw_context": "o).  # noqa: E501  ## Limitations  - The model is trained on academic datasets and may have limitations on certain domain-speci"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "github.io) [![Paper](https://img.shields.io/badge/arXiv-Depth_Anything_3-red)](https://arxiv.org/abs/) [!"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "aeacf407f8ba1fb30cdbdbe8086d95a66ba1b93fb415232c709429cff5b642d7"
    },
    {
      "model_id": "depth-anything/DA3MONO-LARGE",
      "scanned_at": "2026-07-15T02:21:41.515977Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "academic",
          "confidence": 0.6,
          "raw_context": "o).  # noqa: E501  ## Limitations  - The model is trained on academic datasets and may have limitations on certain domain-speci"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "github.io) [![Paper](https://img.shields.io/badge/arXiv-Depth_Anything_3-red)](https://arxiv.org/abs/) [!"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "8f46bb467be6232d362daa71040070f81e6c4f4aff07e7fc7ed05863884b1d82"
    },
    {
      "model_id": "depth-anything/DA3NESTED-GIANT-LARGE-1.1",
      "scanned_at": "2026-07-15T02:21:44.260864Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "academic",
          "confidence": 0.6,
          "raw_context": "o).  # noqa: E501  ## Limitations  - The model is trained on academic datasets and may have limitations on certain domain-speci"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "github.io) [![Paper](https://img.shields.io/badge/arXiv-Depth_Anything_3-red)](https://arxiv.org/abs/) [!"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "cc-by-nc-4.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "af9291386451f59c37065359d450ee75989c84562b84bedf04804e49fb410cf5"
    },
    {
      "model_id": "depth-anything/Depth-Anything-V2-Base",
      "scanned_at": "2026-07-15T02:21:47.001984Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "nd Feng, Jiashi and Zhao, Hengshuang},   journal={arXiv:2406.09414},   year={2024} }  @inproceedings{dept"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "cc-by-nc-4.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "c3dd62000d6cf7fabdc9666d93b2a4d4d70b257426599f3723e0ba63e3957f2f"
    },
    {
      "model_id": "depth-anything/Depth-Anything-V2-Metric-Indoor-Base-hf",
      "scanned_at": "2026-07-15T02:21:49.746257Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "coco",
          "confidence": 0.7,
          "raw_context": "door-Base-hf\")  # load image url = 'http://images.cocodataset.org/val2017/000000039769.jpg' image = Imag"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ntroduced in [the paper of the same name](https://arxiv.org/abs/2406.09414) by Lihe Yang et al. It uses t"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "depth_anything",
          "confidence": 0.5,
          "raw_context": "model_type: depth_anything"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "coco",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.1,
      "provenance_hash": "2801e1b0bc9cdd3fed55001f7001c625e3119557c8599935bc745772904eea2e"
    },
    {
      "model_id": "depth-anything/Depth-Anything-V2-Metric-Indoor-Large-hf",
      "scanned_at": "2026-07-15T02:21:52.501555Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "coco",
          "confidence": 0.7,
          "raw_context": "oor-Large-hf\")  # load image url = 'http://images.cocodataset.org/val2017/000000039769.jpg' image = Imag"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ntroduced in [the paper of the same name](https://arxiv.org/abs/2406.09414) by Lihe Yang et al. It uses t"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "depth_anything",
          "confidence": 0.5,
          "raw_context": "model_type: depth_anything"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "coco",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.1,
      "provenance_hash": "68a69fbdbc9478aa3b4404d89c304ab28366eb3ecd87fbb6b63169b3d57c8994"
    },
    {
      "model_id": "depth-anything/Depth-Anything-V2-Metric-Indoor-Small-hf",
      "scanned_at": "2026-07-15T02:21:55.260474Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "coco",
          "confidence": 0.7,
          "raw_context": "oor-Small-hf\")  # load image url = 'http://images.cocodataset.org/val2017/000000039769.jpg' image = Imag"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ntroduced in [the paper of the same name](https://arxiv.org/abs/2406.09414) by Lihe Yang et al. It uses t"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "depth_anything",
          "confidence": 0.5,
          "raw_context": "model_type: depth_anything"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "coco",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.1,
      "provenance_hash": "a574f4970d6198a83e3cb1af39d953db6f12d58e32e9f9f98d41c9d48511b44b"
    },
    {
      "model_id": "depth-anything/Depth-Anything-V2-Metric-Outdoor-Base-hf",
      "scanned_at": "2026-07-15T02:21:58.021965Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "coco",
          "confidence": 0.7,
          "raw_context": "door-Base-hf\")  # load image url = 'http://images.cocodataset.org/val2017/000000039769.jpg' image = Imag"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ntroduced in [the paper of the same name](https://arxiv.org/abs/2406.09414) by Lihe Yang et al. It uses t"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "depth_anything",
          "confidence": 0.5,
          "raw_context": "model_type: depth_anything"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "coco",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.1,
      "provenance_hash": "a178adc842beb4a88929dab6f7a1729c93e7480d1b3c54e70e3a69358d237571"
    },
    {
      "model_id": "depth-anything/Depth-Anything-V2-Metric-Outdoor-Large-hf",
      "scanned_at": "2026-07-15T02:22:00.861867Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "coco",
          "confidence": 0.7,
          "raw_context": "oor-Large-hf\")  # load image url = 'http://images.cocodataset.org/val2017/000000039769.jpg' image = Imag"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ntroduced in [the paper of the same name](https://arxiv.org/abs/2406.09414) by Lihe Yang et al. It uses t"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "depth_anything",
          "confidence": 0.5,
          "raw_context": "model_type: depth_anything"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "coco",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "46afc63ba340d72327c0c76e1bcb5f5e9f2792d1d29caf5b3f8857a59cbc9b44"
    },
    {
      "model_id": "depth-anything/Depth-Anything-V2-Metric-Outdoor-Small-hf",
      "scanned_at": "2026-07-15T02:22:03.602786Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "coco",
          "confidence": 0.7,
          "raw_context": "oor-Small-hf\")  # load image url = 'http://images.cocodataset.org/val2017/000000039769.jpg' image = Imag"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ntroduced in [the paper of the same name](https://arxiv.org/abs/2406.09414) by Lihe Yang et al. It uses t"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "depth_anything",
          "confidence": 0.5,
          "raw_context": "model_type: depth_anything"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "coco",
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.1,
      "provenance_hash": "051e735d3cb856a0c2f7cf958dda0b03cac9d15291836d0d45edab6870051135"
    },
    {
      "model_id": "depth-anything/Depth-Anything-V2-Small",
      "scanned_at": "2026-07-15T02:22:06.452058Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "nd Feng, Jiashi and Zhao, Hengshuang},   journal={arXiv:2406.09414},   year={2024} }  @inproceedings{dept"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "53250718137a641f7222639e30245dcd86d64b64bcdb67ed2122cffde8bc5c54"
    },
    {
      "model_id": "depth-anything/prompt-depth-anything-vitl-hf",
      "scanned_at": "2026-07-15T02:22:09.196604Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "i and Zhou, Xiaowei and Kang, Bingyi},   journal={arXiv},   year={2024} }"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "prompt_depth_anything",
          "confidence": 0.5,
          "raw_context": "model_type: prompt_depth_anything"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "beceb078e84535d71df806d1e4e207aeb84ff46696de5d0a78f28d466fc92783"
    },
    {
      "model_id": "depth-anything/prompt-depth-anything-vits-hf",
      "scanned_at": "2026-07-15T02:22:11.955652Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "and Zhou, Xiaowei and Kang, Bingyi},\r   journal={arXiv},\r   year={2024}\r }"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "prompt_depth_anything",
          "confidence": 0.5,
          "raw_context": "model_type: prompt_depth_anything"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "1af143720a4437085276c386571b1f9782a08d3c9bbadc099c26ce5b1b8a7656"
    },
    {
      "model_id": "depth-anything/prompt-depth-anything-vits-transparent-hf",
      "scanned_at": "2026-07-15T02:22:14.705355Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "i and Zhou, Xiaowei and Kang, Bingyi},   journal={arXiv},   year={2024} }"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "prompt_depth_anything",
          "confidence": 0.5,
          "raw_context": "model_type: prompt_depth_anything"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "aeea1fd0ec72fe10182e6459d0b37a84e948833bcabac380fe7f132bb809dd15"
    },
    {
      "model_id": "deqing/llama-300M-unigram",
      "scanned_at": "2026-07-15T02:22:17.461198Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "b5acae7adc2453d568aa2f6239314a587cc0552ebb0dd1fc767ff88d7df45efd"
    },
    {
      "model_id": "deqing/llama-300M-v2-bigram",
      "scanned_at": "2026-07-15T02:22:20.222639Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "llama_small_config.json",
      "base_model_chain": [
        "llama_small_config.json"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.4,
      "provenance_hash": "5213564d851bae02749ce29eb55e65ae539631bf5c94adafeca5b7086236ee57"
    },
    {
      "model_id": "deqing/llama-300M-v2-fivegram",
      "scanned_at": "2026-07-15T02:22:24.814037Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "llama_small_config.json",
      "base_model_chain": [
        "llama_small_config.json"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.4,
      "provenance_hash": "64bbef3b1e6a4c367162ade225fd7421bac54b89d17e7f0394982d3c5cb527fa"
    },
    {
      "model_id": "deqing/llama-300M-v2-swap_numbers",
      "scanned_at": "2026-07-15T02:22:27.576299Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "llama_small_config.json",
      "base_model_chain": [
        "llama_small_config.json"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.4,
      "provenance_hash": "ca870a9ac765faaa9918009dbfce9d6da2b5f483bbd0d2ab8bbeb1ba27a1ea23"
    },
    {
      "model_id": "deqing/llama-300M-v2-text_only",
      "scanned_at": "2026-07-15T02:22:30.365734Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "llama_small_config.json",
      "base_model_chain": [
        "llama_small_config.json"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.4,
      "provenance_hash": "58f127bb74f2d1c93ee0dad3eb9ea806cc1ffc7cb659b1a53841024cad237fc6"
    },
    {
      "model_id": "deqing/llama-300M-v2-trigram",
      "scanned_at": "2026-07-15T02:22:33.151328Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "llama_small_config.json",
      "base_model_chain": [
        "llama_small_config.json"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.4,
      "provenance_hash": "436480f54174dccbf4c798e8be788783c8867c657dc0b3f06006de8f4d7837c5"
    },
    {
      "model_id": "deqing/llama-300M-v2-uniform",
      "scanned_at": "2026-07-15T02:22:35.988239Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "llama",
          "confidence": 0.5,
          "raw_context": "model_type: llama"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "llama_small_config.json",
      "base_model_chain": [
        "llama_small_config.json"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.4,
      "provenance_hash": "614428b38d5bfabbefae3014db81eb4b4276dfff535f13ca8da825813498f56c"
    },
    {
      "model_id": "derekhsu/loras",
      "scanned_at": "2026-07-15T02:22:38.785891Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen-Image",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen-Image"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Qwen/Qwen-Image",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Qwen/Qwen-Image"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen-Image",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "08.04: We released the [Technical Report](https://arxiv.org/abs/2508.02324) of Qwen-Image! - 2025.08.04:"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen-Image",
      "base_model_chain": [
        "Qwen/Qwen-Image"
      ],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.15000000000000002,
      "provenance_hash": "54213ab45e62af73cbf67b6d7a008a052d08395c4a9fe895b131c9a2ac257b71"
    },
    {
      "model_id": "destitech/controlnet-inpaint-dreamer-sdxl",
      "scanned_at": "2026-07-15T02:22:43.615350Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "openrail",
      "provenance_score": 0.1,
      "provenance_hash": "7f1bf2eb7f75824339ab0fb32e2bcb7a388e04b45fe0162b9bc711febaa8415b"
    },
    {
      "model_id": "devika-tiwari/gpt2_small_expandedbabyLM_100M_adj_150percent_43",
      "scanned_at": "2026-07-15T02:22:46.376958Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.3,
      "provenance_hash": "cb44cb535d12b3599bf9cc1fbc324d0b8cc48a407388c601e778b8164bc6baa2"
    },
    {
      "model_id": "devika-tiwari/gpt2_small_expandedbabyLM_100M_cnp_25percent_43",
      "scanned_at": "2026-07-15T02:22:49.168084Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.3,
      "provenance_hash": "69bafff82b3f87cf0a6d88eb12033a476918ba9d637724b1f0556945e6e4ffe5"
    },
    {
      "model_id": "devika-tiwari/gpt2_small_expandedbabyLM_100M_sentsubj_25percent_43",
      "scanned_at": "2026-07-15T02:22:51.990552Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "gpt2",
          "confidence": 0.5,
          "raw_context": "model_type: gpt2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.3,
      "provenance_hash": "0d50a22d5670447e5530e736ed0ac6dc254f8192900acd79e50e071cdfe611a4"
    },
    {
      "model_id": "dherain24/HelixMind-ckpts",
      "scanned_at": "2026-07-15T02:22:54.736276Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "759a32a94e6176823e69bc3ff4f8d4979a4cee23f22253599673407e6c761c7f"
    },
    {
      "model_id": "dieg0code/ataxx-zero",
      "scanned_at": "2026-07-15T02:22:57.563337Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.1,
      "provenance_hash": "010bb2ba223af176890fb7f7874a4b5d35d219bca868f7e771c45ec23c3d53d3"
    },
    {
      "model_id": "dieptrongtuan93/2olutd1fOOFcSZN",
      "scanned_at": "2026-07-15T02:23:00.329651Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "48cdc95c0bb6223567d292ad4e56141955eaf35127822159dfaf0a3f3352c8bc"
    },
    {
      "model_id": "dieptrongtuan93/6uqLRoIjdUAsYZc",
      "scanned_at": "2026-07-15T02:23:03.075308Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "8fa654e33cde0edc8bb4fc747fb7c5d5b35f8064666406e5efe721bf138671d1"
    },
    {
      "model_id": "dieptrongtuan93/UWA6TFMD8U9lNKI",
      "scanned_at": "2026-07-15T02:23:05.813698Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "645bdf4e4e0604f038a2174bb3cf96996450ab343fc16fb6e1835281a97bb5b5"
    },
    {
      "model_id": "diffusers/FLUX.2-dev-bnb-4bit",
      "scanned_at": "2026-07-15T02:23:08.551527Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "c3d5fbaf8c1a8f10a133a9542e4c04effcd5b1e5a49670907eeb2fd14f7129f8"
    },
    {
      "model_id": "diffusers/stable-diffusion-xl-1.0-inpainting-0.1",
      "scanned_at": "2026-07-15T02:23:11.307840Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "stabilityai/stable-diffusion-xl-base-1.0",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:stabilityai/stable-diffusion-xl-base-1.0"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:stabilityai/stable-diffusion-xl-base-1.0",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "stabilityai/stable-diffusion-xl-base-1.0",
          "confidence": 0.85,
          "raw_context": "--- license: openrail++ base_model: stabilityai/stable-diffusion-xl-base-1.0 tags: - stable-diffusion-xl - stable-diffusion-xl"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses two fixed, pretrain"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:stabilityai/stable-diffusion-xl-base-1.0",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "Model  ![pipeline](pipeline.png)  [SDXL](https://arxiv.org/abs/2307.01952) consists of an [ensemble of e"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "stabilityai/stable-diffusion-xl-base-1.0",
      "base_model_chain": [
        "stabilityai/stable-diffusion-xl-base-1.0"
      ],
      "training_section_present": false,
      "license": "openrail++",
      "provenance_score": 0.25,
      "provenance_hash": "6775ac1e3e245ccf685b2cbb67c7f0768f797d5d416a44492fe64d5c07876fd6"
    },
    {
      "model_id": "digiplay/Photon_v1",
      "scanned_at": "2026-07-15T02:23:15.891150Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "6e58013a5a376845aff2699a2888392ae954807b1f6d399e6f636db439a342a8"
    },
    {
      "model_id": "dima806/deepfake_vs_real_image_detection",
      "scanned_at": "2026-07-15T02:23:18.645331Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "google/vit-base-patch16-224-in21k",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:google/vit-base-patch16-224-in21k"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:google/vit-base-patch16-224-in21k",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:google/vit-base-patch16-224-in21k"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "dima806/deepfake_vs_real_image_detection",
          "confidence": 0.9,
          "raw_context": "_name_or_path: dima806/deepfake_vs_real_image_detection"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "vit",
          "confidence": 0.5,
          "raw_context": "model_type: vit"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:google/vit-base-patch16-224-in21k",
          "value": "imagenet",
          "confidence": 0.5599999999999999,
          "raw_context": "-- license: apache-2.0 tags: - vision datasets: - imagenet-21k inference: false ---  # Vision Transformer (b"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:google/vit-base-patch16-224-in21k",
          "value": "coco",
          "confidence": 0.5599999999999999,
          "raw_context": "mport Image import requests  url = 'http://images.cocodataset.org/val2017/000000039769.jpg' image = Imag"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:google/vit-base-patch16-224-in21k",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "nsformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Dosovitskiy et al. and fir"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "imagenet",
        "coco",
        "arxiv"
      ],
      "base_model": "google/vit-base-patch16-224-in21k",
      "base_model_chain": [
        "google/vit-base-patch16-224-in21k"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.35000000000000003,
      "provenance_hash": "80eba67b8a874e57091919e0aa05ec96f164d5892e437b1d57e469072ec8a3a6"
    },
    {
      "model_id": "dima806/english_accents_classification",
      "scanned_at": "2026-07-15T02:23:23.219104Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "facebook/wav2vec2-base-960h",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:facebook/wav2vec2-base-960h"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:facebook/wav2vec2-base-960h",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:facebook/wav2vec2-base-960h"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "dima806/english_accents_classification",
          "confidence": 0.9,
          "raw_context": "_name_or_path: dima806/english_accents_classification"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "wav2vec2",
          "confidence": 0.5,
          "raw_context": "model_type: wav2vec2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:facebook/wav2vec2-base-960h",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "input is also sampled at 16Khz.  [Paper](https://arxiv.org/abs/2006.11477)  Authors: Alexei Baevski, Hen"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "facebook/wav2vec2-base-960h",
      "base_model_chain": [
        "facebook/wav2vec2-base-960h"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.25,
      "provenance_hash": "133b8319ba98b7635ff9be9a4f716f53015d8a37e488340c35359170adeb15aa"
    },
    {
      "model_id": "dima806/music_genres_classification",
      "scanned_at": "2026-07-15T02:23:27.795894Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "facebook/wav2vec2-base-960h",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:facebook/wav2vec2-base-960h"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:facebook/wav2vec2-base-960h",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:facebook/wav2vec2-base-960h"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.6,
          "raw_context": "k/wav2vec2-base-960h --- [Music genre](https://en.wikipedia.org/wiki/Music_genre) classification is a fundame"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "wikipedia",
          "confidence": 0.7,
          "raw_context": "k/wav2vec2-base-960h --- [Music genre](https://en.wikipedia.org/wiki/Music_genre) classification is a fundame"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "facebook/wav2vec2-base-960h",
          "confidence": 0.9,
          "raw_context": "_name_or_path: facebook/wav2vec2-base-960h"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "wav2vec2",
          "confidence": 0.5,
          "raw_context": "model_type: wav2vec2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:facebook/wav2vec2-base-960h",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "input is also sampled at 16Khz.  [Paper](https://arxiv.org/abs/2006.11477)  Authors: Alexei Baevski, Hen"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "wikipedia",
        "arxiv"
      ],
      "base_model": "facebook/wav2vec2-base-960h",
      "base_model_chain": [
        "facebook/wav2vec2-base-960h"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "b2bbd9fa19fb27bb350d14bafd008e4cc5af224d0526c35428c2a7764ae91e9e"
    },
    {
      "model_id": "diyorbek95/misaz666",
      "scanned_at": "2026-07-15T02:23:30.536973Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "2cf18ca3110a3331cfcb4c1ef81aad65eb49e426d3fe3cfc07d41e4740b54a24"
    },
    {
      "model_id": "djovak/embedic-base",
      "scanned_at": "2026-07-15T02:23:33.345895Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "intfloat/multilingual-e5-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:intfloat/multilingual-e5-base"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:intfloat/multilingual-e5-base",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:intfloat/multilingual-e5-base"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "mC4",
          "confidence": 0.48,
          "raw_context": "-------------------|-----------------| | Filtered [mC4](https://huggingface.co/datasets/mc4)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "NLLB",
          "confidence": 0.48,
          "raw_context": "ws content)                 | 400M            | | [NLLB](https://huggingface.co/datasets/allenai/nllb)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "Wikipedia",
          "confidence": 0.48,
          "raw_context": "n pairs                     | 2.4B            | | [Wikipedia](https://huggingface.co/datasets/intfloat/wikipedia)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "xP3",
          "confidence": 0.48,
          "raw_context": "answer)                    | 50M             | | [xP3](https://huggingface.co/datasets/bigscience/xP3)"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "ELI5",
          "confidence": 0.48,
          "raw_context": "| English      | <300k           | | [ELI5](https://huggingface.co/datasets/eli5)                                           |"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "SQuAD",
          "confidence": 0.48,
          "raw_context": "| English      | 70k             | | [SQuAD](https://huggingface.co/datasets/squad)                                         | E"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "Quora",
          "confidence": 0.48,
          "raw_context": "| English      | 87k             | | [Quora](https://huggingface.co/datasets/quora)                                         | E"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "MIRACL",
          "confidence": 0.48,
          "raw_context": "| 11 languages | 50k             | | [MIRACL](https://huggingface.co/datasets/miracl/miracl)"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "squad",
          "confidence": 0.5599999999999999,
          "raw_context": "| English      | 70k             | | [SQuAD](https://huggingface.co/datasets/squad)"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "c4",
          "confidence": 0.5599999999999999,
          "raw_context": "onfig: af       split: test       revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7     metrics:"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "type: Clustering     dataset:       type: mteb/arxiv-clustering-p2p       name: MTEB ArxivClusteringP2"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "wikipedia",
          "confidence": 0.5599999999999999,
          "raw_context": "pairs                     | 2.4B            | | [Wikipedia](https://huggingface.co/datasets/intfloat/wikiped"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:intfloat/multilingual-e5-base",
          "value": "mc4",
          "confidence": 0.5599999999999999,
          "raw_context": "------------------|-----------------| | Filtered [mC4](https://huggingface.co/datasets/mc4)"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "mC4",
        "Quora",
        "wikipedia",
        "ELI5",
        "MIRACL",
        "xP3",
        "squad",
        "Wikipedia",
        "SQuAD",
        "arxiv",
        "mc4",
        "NLLB"
      ],
      "base_model": "intfloat/multilingual-e5-base",
      "base_model_chain": [
        "intfloat/multilingual-e5-base"
      ],
      "training_section_present": false,
      "license": "mit",
      "provenance_score": 0.4,
      "provenance_hash": "5c77d2a577ff964b23b9b4fc2f04baab6ce1200c136c03516362295ff58cfba3"
    },
    {
      "model_id": "dkl4/llm2025-qwen3-4b-structured-output-lora-01-v5",
      "scanned_at": "2026-07-15T02:23:38.012680Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "u-10bei/structured_data_with_cot_dataset_512_v5",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:u-10bei/structured_data_with_cot_dataset_512_v5"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "unsloth/Qwen3-4B-Instruct-2507",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:unsloth/Qwen3-4B-Instruct-2507"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:unsloth/Qwen3-4B-Instruct-2507",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:unsloth/Qwen3-4B-Instruct-2507"
        },
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "u-10bei/structured_data_with_cot_dataset_512_v5",
          "confidence": 0.8,
          "raw_context": "er) ```  ## Sources & Terms (IMPORTANT)  Training data: u-10bei/structured_data_with_cot_dataset_512_v5  Dataset License: MIT License. This dataset is us"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "unsloth/Qwen3-4B-Instruct-2507",
          "confidence": 0.85,
          "raw_context": "--- base_model: unsloth/Qwen3-4B-Instruct-2507 datasets: - u-10bei/structured_data_with_cot_data"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "Qwen/Qwen3-4B-Instruct-2507",
          "confidence": 0.85,
          "raw_context": "**. The base model must be loaded separately  --- base_model: Qwen/Qwen3-4B-Instruct-2507 datasets: - u-10bei/structured_data_with_cot_data"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "unsloth/Qwen3-4B-Instruct-2507",
          "confidence": 0.85,
          "raw_context": "Thought) is masked.  ## Training Configuration  - Base model: unsloth/Qwen3-4B-Instruct-2507 - Method: QLoRA (4-bit) - Max sequence length: 51"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:unsloth/Qwen3-4B-Instruct-2507",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [
        "u-10bei/structured_data_with_cot_dataset_512_v5"
      ],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "unsloth/Qwen3-4B-Instruct-2507",
      "base_model_chain": [
        "unsloth/Qwen3-4B-Instruct-2507",
        "Qwen/Qwen3-4B-Instruct-2507"
      ],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.65,
      "provenance_hash": "e0111a98e3201e2b4e922421e6969478e449f4e5f06f391a904c1b5c4359bdde"
    },
    {
      "model_id": "dmis-lab/biobert-base-cased-v1.2",
      "scanned_at": "2026-07-15T02:23:40.795960Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "bert",
          "confidence": 0.5,
          "raw_context": "model_type: bert"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "258807ddb1c7b00310bc6ca9baa002149f91715409ef006b1f7bf98e25a308cb"
    },
    {
      "model_id": "dmsnoa/Simple_BS",
      "scanned_at": "2026-07-15T02:23:43.540048Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "87cd4b575964bcbe7a36fd905291c7f65a84fcdfb8bf8ce9e0563b83d1da5635"
    },
    {
      "model_id": "dmsnoa/Simple_TFBS",
      "scanned_at": "2026-07-15T02:23:46.471826Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "other",
      "provenance_score": 0.1,
      "provenance_hash": "6b0d21b1fb89e858a4786744a934acd428965e0d492e90c42adb039a740b56f2"
    },
    {
      "model_id": "dobrien/ViT-B-32-GTSRB-dummy-TINet-0.01",
      "scanned_at": "2026-07-15T02:23:49.257274Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "imagenet",
          "confidence": 0.7,
          "raw_context": "t         ## Dummy Dataset Location: zh-plus/tiny-imagenet         ## Loss Term: 1e-2         ## Merge Metho"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "imagenet"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.35,
      "provenance_hash": "3317d66a08057d77e19a9043bf30d96dea81b6c5d7ad6bbfebb9c89e8e004ea7"
    },
    {
      "model_id": "doikhuonghoan/9vm0y8EjvexaQuA",
      "scanned_at": "2026-07-15T02:23:52.344907Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "2dc6ed6b9506950e2bc62fd31fc3e378528e9563f3732a867cd996a42750aaee"
    },
    {
      "model_id": "doikhuonghoan/CF0UcyTjRlCvXhV",
      "scanned_at": "2026-07-15T02:23:55.079423Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "64e77d7e39a1a2d97f132fd0d2f6b414b83c88708a5ccdfd72f9161b45559952"
    },
    {
      "model_id": "doikhuonghoan/aOzf1GzIkrfqnff",
      "scanned_at": "2026-07-15T02:23:57.813445Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "e2a4185456381b23ca4e7424a8b2641d7f8cdec9f60fc6c1c98a93547ecf0f62"
    },
    {
      "model_id": "dongwenpu/sage_attention",
      "scanned_at": "2026-07-15T02:24:00.544529Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.1,
      "provenance_hash": "e665de06520f49926681f852ae8ba15588f4c6f14239b127121ddb2b8b0c4559"
    },
    {
      "model_id": "dperales/layoutlmv2-base-uncased_finetuned_docvqa",
      "scanned_at": "2026-07-15T02:24:03.299746Z",
      "signals": [
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "microsoft/layoutlmv2-base-uncased",
          "confidence": 0.9,
          "raw_context": "_name_or_path: microsoft/layoutlmv2-base-uncased"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "layoutlmv2",
          "confidence": 0.5,
          "raw_context": "model_type: layoutlmv2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "df0ae837da8e3fa5872e4e0ce6bf71f6199a76e095f53e551c36cd15028e74b4"
    },
    {
      "model_id": "dphnAI/32B-full",
      "scanned_at": "2026-07-15T02:24:06.073131Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "olmo3",
          "confidence": 0.5,
          "raw_context": "model_type: olmo3"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "bf7de376a5b6a6ce6ae22abe571354031064a36c1b00839d0d966e68463bfd14"
    },
    {
      "model_id": "dphnAI/32B-gguf",
      "scanned_at": "2026-07-15T02:24:08.840434Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "d9b3e952586d12009a9663de05c92049ff3fb0031c17c3454976ebff2c9df26c"
    },
    {
      "model_id": "dsba-lab/koreapas-finetuned-korwikitq",
      "scanned_at": "2026-07-15T02:24:11.607988Z",
      "signals": [
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "tapas",
          "confidence": 0.5,
          "raw_context": "model_type: tapas"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "49b4e7efe2a21e94f2d2a5e705a656b0acbce7923de92cdd6589421eab9b1d56"
    },
    {
      "model_id": "dseditor/Qwen3-ASR-1.7B-INT8_OpenVINO",
      "scanned_at": "2026-07-15T02:24:14.379768Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-ASR-1.7B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-ASR-1.7B"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Qwen/Qwen3-ASR-1.7B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Qwen/Qwen3-ASR-1.7B"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "token IDs for prompt construction\r vocab.json / merges.txt                      BPE toke"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3_asr",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3_asr"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-ASR-1.7B",
          "value": "voc",
          "confidence": 0.5599999999999999,
          "raw_context": "<tr>       <td style=\"text-align: left;\">MIR-1k-vocal</td>       <td style=\"text-align: center;\">11.8"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-ASR-1.7B",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "g, Jin Xu, Jingren Zhou, Junyang Lin},   journal={arXiv preprint arXiv:2601.21337},   year={2026} } ```"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-ASR-1.7B",
      "base_model_chain": [
        "Qwen/Qwen3-ASR-1.7B"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "739d0d091e654ef0629f1637a2f6279f439af882c67b0e53efd5651d9e7e66ff"
    },
    {
      "model_id": "dukal1s/sara",
      "scanned_at": "2026-07-15T02:24:19.019638Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "2bc7df815018d357c7cdf68d619fd9643f0f143b68d7e02a4747696a8df3d3d4"
    },
    {
      "model_id": "duongthichau808/0tQV02fo9p6XJ6c",
      "scanned_at": "2026-07-15T02:24:21.785547Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "02d7bb199dc0097617429a4acf3660d04b1fe12f0396032ac26ae956a5402ba1"
    },
    {
      "model_id": "duongthichau808/4zdSrXoVvvRcqkF",
      "scanned_at": "2026-07-15T02:24:24.517508Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "f609274b893d3fe848c191d642a3fd9816021c121aa44b9138ba683fbbe35486"
    },
    {
      "model_id": "duongthichau808/RH5ciOj4CH7DvdX",
      "scanned_at": "2026-07-15T02:24:27.249221Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "c0f6e560603b2fcc102d7776e1ff17b63aee2908122907f102eacbd644062293"
    },
    {
      "model_id": "duongve/NetaYume-Lumina-Image-2.0",
      "scanned_at": "2026-07-15T02:24:29.987963Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Alpha-VLLM/Lumina-Image-2.0",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Alpha-VLLM/Lumina-Image-2.0"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Alpha-VLLM/Lumina-Image-2.0",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Alpha-VLLM/Lumina-Image-2.0"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Alpha-VLLM/Lumina-Image-2.0",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "and Efficient Image Generative Framework](https://arxiv.org/abs/2503.21758).  ## Citation  If you find th"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Alpha-VLLM/Lumina-Image-2.0",
      "base_model_chain": [
        "Alpha-VLLM/Lumina-Image-2.0"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.25,
      "provenance_hash": "b09208fa192df9e3149c017154c60ec8c9f3e4613cbf4006be8d534054da122d"
    },
    {
      "model_id": "dx8152/Qwen-Edit-2509-Light-Migration",
      "scanned_at": "2026-07-15T02:24:34.565720Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen-Image-Edit-2509",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2508.02324},       archivePrefix={arXiv},       primaryClass={cs.CV},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen-Image-Edit-2509",
      "base_model_chain": [
        "Qwen/Qwen-Image-Edit-2509"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.25,
      "provenance_hash": "c15c34c135d4efd3a1b9c223d2e4344ff03ee2844920079b4b3417153c27e9e8"
    },
    {
      "model_id": "dx8152/Qwen-Edit-2509-Multi-Angle-Lighting",
      "scanned_at": "2026-07-15T02:24:39.364904Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen-Image-Edit-2509",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2508.02324},       archivePrefix={arXiv},       primaryClass={cs.CV},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen-Image-Edit-2509",
      "base_model_chain": [
        "Qwen/Qwen-Image-Edit-2509"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.25,
      "provenance_hash": "17d688434193eb1b1e973cea9f0385861b7bb73ac5de501d4531bffa37ae2df0"
    },
    {
      "model_id": "dx8152/Qwen-Image-Edit-2509-Fusion",
      "scanned_at": "2026-07-15T02:24:42.140937Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen-Image-Edit-2509",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2508.02324},       archivePrefix={arXiv},       primaryClass={cs.CV},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen-Image-Edit-2509",
      "base_model_chain": [
        "Qwen/Qwen-Image-Edit-2509"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.25,
      "provenance_hash": "9e4076ae73d3d55f66044b159efad1e73198bee685b15df3d79bedc48a96e3ee"
    },
    {
      "model_id": "dx8152/Qwen-Image-Edit-2509-Light_restoration",
      "scanned_at": "2026-07-15T02:24:44.895929Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "c4",
          "confidence": 0.7,
          "raw_context": "roduction/uploads/64461e86ab86b035add67e41/nPg_W7KC4dfNoQl5PApF8.png) ![ComfyUI_temp_gpvja_00007_](htt"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen-Image-Edit-2509",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2508.02324},       archivePrefix={arXiv},       primaryClass={cs.CV},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "c4",
        "arxiv"
      ],
      "base_model": "Qwen/Qwen-Image-Edit-2509",
      "base_model_chain": [
        "Qwen/Qwen-Image-Edit-2509"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "8d52788df0d4e560d7f3bef119f6753f70b93da117e09bb42dd554905590a27c"
    },
    {
      "model_id": "dx8152/Qwen-Image-Edit-2509-Relight",
      "scanned_at": "2026-07-15T02:24:47.661115Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:Qwen/Qwen-Image-Edit-2509",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:Qwen/Qwen-Image-Edit-2509"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "n/uploads/64461e86ab86b035add67e41/9OrnI-2SKWhtYezVocKSV.png)"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen-Image-Edit-2509",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2508.02324},       archivePrefix={arXiv},       primaryClass={cs.CV},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "voc",
        "arxiv"
      ],
      "base_model": "Qwen/Qwen-Image-Edit-2509",
      "base_model_chain": [
        "Qwen/Qwen-Image-Edit-2509"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.30000000000000004,
      "provenance_hash": "9ca67a033bc2c2cd6cbd57cac56f5671dbbcc5c905cd2f7f0f203d7f88b53a6a"
    },
    {
      "model_id": "dzur658/ping-technical-assistant-LoRA-001-GGUF",
      "scanned_at": "2026-07-15T02:24:50.412811Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-1.7B-GGUF",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-1.7B-GGUF"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "quantized:Qwen/Qwen3-1.7B-GGUF",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:quantized:Qwen/Qwen3-1.7B-GGUF"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": "Qwen/Qwen3-1.7B-GGUF",
      "base_model_chain": [
        "Qwen/Qwen3-1.7B-GGUF",
        "Qwen/Qwen3-1.7B",
        "Qwen/Qwen3-1.7B-Base"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.2,
      "provenance_hash": "d47a4f9871cb611544110303116c6c6589b18a809880c41584112605df33c873"
    },
    {
      "model_id": "dzur658/ping-technical-assistant-LoRA-001-MLX",
      "scanned_at": "2026-07-15T02:24:55.940456Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "Qwen/Qwen3-1.7B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:Qwen/Qwen3-1.7B"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:Qwen/Qwen3-1.7B",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:Qwen/Qwen3-1.7B"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:Qwen/Qwen3-1.7B",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": ",       eprint={2505.09388},       archivePrefix={arXiv},       primaryClass={cs.CL},       url={https://"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "Qwen/Qwen3-1.7B",
      "base_model_chain": [
        "Qwen/Qwen3-1.7B",
        "Qwen/Qwen3-1.7B-Base"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.25,
      "provenance_hash": "083ff59512fd6d5bea2742dbc342227bb1a0e73b7f5b7aa8fc967429927875b6"
    },
    {
      "model_id": "eac123/subliminal-10k-anteaters10000",
      "scanned_at": "2026-07-15T02:24:59.622831Z",
      "signals": [
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "adapter:google/gemma-3-4b-it",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:adapter:google/gemma-3-4b-it"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "google/gemma-3-4b-it",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:google/gemma-3-4b-it"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "google/gemma-3-4b-it",
          "confidence": 0.85,
          "raw_context": "--- base_model: google/gemma-3-4b-it library_name: peft pipeline_tag: text-generation"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "ute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).  - **Hardware Type:** [More"
        },
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": "adapter:google/gemma-3-4b-it",
      "base_model_chain": [
        "adapter:google/gemma-3-4b-it"
      ],
      "training_section_present": true,
      "license": null,
      "provenance_score": 0.45,
      "provenance_hash": "964fdf6cd1d48adccd880fe45b9f2a243cb9be9a1c4bb4c7226fefe98b0c4ee6"
    },
    {
      "model_id": "edbeeching/decision-transformer-gym-hopper-expert",
      "scanned_at": "2026-07-15T02:25:04.204580Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "This is a trained [Decision Transformer](https://arxiv.org/abs/2106.01345) model trained on expert traje"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "edbeeching/decision-transformer-gym-hopper-expert",
          "confidence": 0.9,
          "raw_context": "_name_or_path: edbeeching/decision-transformer-gym-hopper-expert"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "decision_transformer",
          "confidence": 0.5,
          "raw_context": "model_type: decision_transformer"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "3cefcdef395f3ae960e4a2126b991ce89a1b1a61d25c1a789a0e03b9c1d6faa4"
    },
    {
      "model_id": "edbeeching/decision-transformer-gym-hopper-medium",
      "scanned_at": "2026-07-15T02:25:06.945302Z",
      "signals": [
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "arxiv",
          "confidence": 0.7,
          "raw_context": "This is a trained [Decision Transformer](https://arxiv.org/abs/2106.01345) model trained on medium traje"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "edbeeching/decision-transformer-gym-hopper-medium",
          "confidence": 0.9,
          "raw_context": "_name_or_path: edbeeching/decision-transformer-gym-hopper-medium"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "decision_transformer",
          "confidence": 0.5,
          "raw_context": "model_type: decision_transformer"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [
        "arxiv"
      ],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.05,
      "provenance_hash": "543e974072f7388746916777244c837cb87fc49b59728eaae54531ac2dac1086"
    },
    {
      "model_id": "eddiegulay/wav2vec2-large-xlsr-mvc-swahili",
      "scanned_at": "2026-07-15T02:25:09.682445Z",
      "signals": [
        {
          "signal_type": "tag",
          "source": "hf_api_tags",
          "value": "common_voice_13_0",
          "confidence": 0.95,
          "raw_context": "Tag: dataset:common_voice_13_0"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "facebook/wav2vec2-large-xlsr-53",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:facebook/wav2vec2-large-xlsr-53"
        },
        {
          "signal_type": "base_model_tag",
          "source": "hf_api_tags",
          "value": "finetune:facebook/wav2vec2-large-xlsr-53",
          "confidence": 0.99,
          "raw_context": "Tag: base_model:finetune:facebook/wav2vec2-large-xlsr-53"
        },
        {
          "signal_type": "readme_base_model",
          "source": "model_card",
          "value": "facebook/wav2vec2-large-xlsr-53",
          "confidence": 0.85,
          "raw_context": "--- license: apache-2.0 base_model: facebook/wav2vec2-large-xlsr-53 tags: - generated_from_trainer datasets: - common"
        },
        {
          "signal_type": "known_dataset",
          "source": "model_card",
          "value": "voc",
          "confidence": 0.7,
          "raw_context": "# How to use the model  There was an issue with vocab, seems like there are special characters includ"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "alamsher/wav2vec2-large-xlsr-53-common-voice-sw",
          "confidence": 0.9,
          "raw_context": "_name_or_path: alamsher/wav2vec2-large-xlsr-53-common-voice-sw"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "wav2vec2",
          "confidence": 0.5,
          "raw_context": "model_type: wav2vec2"
        },
        {
          "signal_type": "inherited_readme_dataset",
          "source": "base_model:facebook/wav2vec2-large-xlsr-53",
          "value": "labeled",
          "confidence": 0.48,
          "raw_context": "s shared across languages. The resulting model is fine-tuned on labeled data and experiments show that cross-lingual pretraini"
        },
        {
          "signal_type": "inherited_known_dataset",
          "source": "base_model:facebook/wav2vec2-large-xlsr-53",
          "value": "arxiv",
          "confidence": 0.5599999999999999,
          "raw_context": "2-english) for more information.  [Paper](https://arxiv.org/abs/2006.13979)  Authors: Alexis Conneau, Ale"
        }
      ],
      "declared_datasets": [
        "common_voice_13_0"
      ],
      "inferred_datasets": [
        "voc",
        "labeled",
        "arxiv"
      ],
      "base_model": "facebook/wav2vec2-large-xlsr-53",
      "base_model_chain": [
        "facebook/wav2vec2-large-xlsr-53"
      ],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.45000000000000007,
      "provenance_hash": "a9ffe22e4f902057b9e6f2d32454714a822e9869fb8bb88f8b84497a3e6a732a"
    },
    {
      "model_id": "edgarcancinoe/xvla-base_finetuned_soarm101_pickplace_10d_so101_ee6d_a-m_s-i",
      "scanned_at": "2026-07-15T02:25:14.458339Z",
      "signals": [],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": null,
      "provenance_score": 0.0,
      "provenance_hash": "85921e7f85c18acb4c5fce7bb854908697144d3358c10080f6129ec0f47abf8b"
    },
    {
      "model_id": "ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition",
      "scanned_at": "2026-07-15T02:25:17.185832Z",
      "signals": [
        {
          "signal_type": "training_section",
          "source": "model_card",
          "value": "present",
          "confidence": 1.0,
          "raw_context": "Training section found in README"
        },
        {
          "signal_type": "config_base",
          "source": "config.json",
          "value": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
          "confidence": 0.9,
          "raw_context": "_name_or_path: jonatasgrosman/wav2vec2-large-xlsr-53-english"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "wav2vec2",
          "confidence": 0.5,
          "raw_context": "model_type: wav2vec2"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": true,
      "license": "apache-2.0",
      "provenance_score": 0.4,
      "provenance_hash": "b556fa9ba227fba998f86145a0fda04d6a40d175a607418cd54f4ad65440934e"
    },
    {
      "model_id": "ekwek/Soprano-1.1-80M",
      "scanned_at": "2026-07-15T02:25:19.962069Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "more",
          "confidence": 0.6,
          "raw_context": "occur. This is expected to diminish as Soprano is trained on more data.  ---  ## License  This project is licensed under"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.1,
      "provenance_hash": "871d431cd421389128e6493973dbef899195a17bc06b9c0103149f49f72e48b2"
    },
    {
      "model_id": "ekwek/Soprano-80M",
      "scanned_at": "2026-07-15T02:25:22.759480Z",
      "signals": [
        {
          "signal_type": "readme_dataset",
          "source": "model_card",
          "value": "more",
          "confidence": 0.6,
          "raw_context": "occur. This is expected to diminish as Soprano is trained on more data.  ---  ## License  This project is licensed under"
        },
        {
          "signal_type": "model_type",
          "source": "config.json",
          "value": "qwen3",
          "confidence": 0.5,
          "raw_context": "model_type: qwen3"
        }
      ],
      "declared_datasets": [],
      "inferred_datasets": [],
      "base_model": null,
      "base_model_chain": [],
      "training_section_present": false,
      "license": "apache-2.0",
      "provenance_score": 0.1,
      "provenance_hash": "992b08d8779d6739de06c93026b44f7fe0c00dbee67fe2a6e0a9fa520b68a51a"
    }
  ]
}