{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "medical-o1-reasoning-sft",
  "name": "medical-o1-reasoning-SFT（中文子集）",
  "summary": {
    "zh": "许可证声明：宽松（Apache-2.0）；本站处理：只链接原出处。许可证宽松，但有来源风险：由模型生成，需核对所用模型的输出使用条款；只链接原出处。",
    "en": "License: permissive (Apache-2.0); Mdexa hosting: link-only. License is permissive, but source risk: generated by a model; the model's output terms need checking; link only."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "qa-dialogue"
  ],
  "content_description": {
    "en": "QA and reasoning fine-tuning data",
    "zh": "问答与推理微调数据"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "中文 zh 子集20.2k条、zh_mix 25.4k条（另有英文子集）",
    "measures": [
      {
        "value": 20200,
        "unit": "items",
        "qualifier": "approx",
        "scope": "zh subset"
      },
      {
        "value": 25400,
        "unit": "items",
        "qualifier": "approx",
        "scope": "zh_mix subset"
      }
    ]
  },
  "publisher": "FreedomIntelligence（HuatuoGPT-o1）",
  "year": {
    "value": 2024,
    "raw": "2024（arXiv 2412.18925）"
  },
  "expert_review": {
    "en": "Checked by an automated medical verifier",
    "zh": "由自动化的医学验证器校验"
  },
  "license": {
    "legacy_status": "distributable",
    "spdx": "Apache-2.0",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "Dataset card states Apache-2.0",
      "zh": "数据集卡为 Apache-2.0"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Hugging Face dataset card metadata: Apache-2.0",
          "zh": "Hugging Face 数据集卡元数据：Apache-2.0"
        },
        "excerpt": "license: apache-2.0",
        "spdx": "Apache-2.0",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "zh": "许可证宽松，但有来源风险：由模型生成，需核对所用模型的输出使用条款；只链接原出处。",
    "en": "License is permissive, but source risk: generated by a model; the model's output terms need checking; link only."
  },
  "signoff": null,
  "risk_flags": [
    "model-generated"
  ],
  "provenance": {
    "source_description": {
      "en": "Based on verifiable medical problems; reasoning and answers generated by GPT-4o",
      "zh": "基于医学可验证问题，GPT-4o 生成推理与答案"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "Answers generated by GPT-4o; the terms for using OpenAI-generated content were not checked",
      "zh": "答案由 GPT-4o 生成，使用 OpenAI 生成内容的条款本次未核"
    },
    {
      "en": "Source of the underlying questions not checked",
      "zh": "底层题目来源本次未核"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": [
      "arXiv:2412.18925"
    ]
  },
  "verification_level": "verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "intended_use",
      "value": "fine-tuning",
      "basis": "author-stated",
      "excerpt": "This dataset is used to fine-tune HuatuoGPT-o1, a medical LLM designed for advanced medical reasoning. This dataset is constructed using",
      "snapshot_id": "s01"
    },
    {
      "facet": "annotation_depth",
      "value": "with-reasoning",
      "basis": "author-stated",
      "excerpt": "[2024/12/25] We open-sourced the medical reasoning dataset for SFT, built on medical verifiable problems and an LLM verifier.",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "json",
      "basis": "author-stated",
      "excerpt": "data_files: medical_o1_sft_Chinese.json",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "open-qa",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Verifiable questions with reasoning.",
        "zh": "可验证医学问题+推理+回答"
      }
    },
    {
      "facet": "expert_involvement",
      "value": "none",
      "basis": "inferred",
      "inferred_from": "card-source",
      "note": {
        "en": "Reasoning generated by model.",
        "zh": "推理由模型生成"
      }
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "zh": "综合医学推理题，未限定专科",
        "en": "综合医学推理题; not limited to a specialty"
      }
    }
  ],
  "changelog": [
    {
      "date": "2026-11-12",
      "change": {
        "en": "Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.",
        "zh": "由早期人工整理的目录转换生成，未新增事实；按分类体系 v2 重新归类。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.",
        "zh": "把许可证状态拆成 license_status（许可证怎么写）与 hosting（本站怎么处理）；原结论保留以便追溯。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.",
        "zh": "补入来自已抓取页面快照的许可证逐字摘录与快照编号；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 6 (3 stated by the authors with excerpts, 3 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 6 个（作者声明 3 个，附逐字摘录；据内容推断 3 个）；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Removed the stored size-tier tag; the tier is now computed from the size field when pages are built.",
        "zh": "移除存储的规模档位标签；档位改为生成页面时由 size 字段计算。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added specialty tags: multi-specialty(inferred).",
        "zh": "新增专科标签：multi-specialty(inferred)。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "FreedomIntelligence/medical-o1-reasoning-SFT",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/FreedomIntelligence/medical-o1-reasoning-SFT",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT/resolve/fc2c9e8a37b38f38da6d449564a8c350b244aef4/.gitattributes",
        "size_bytes": 2504,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT/resolve/fc2c9e8a37b38f38da6d449564a8c350b244aef4/README.md",
        "size_bytes": 1967,
        "checksum": null,
        "format": "md"
      },
      {
        "name": "medical_o1_sft.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT/resolve/fc2c9e8a37b38f38da6d449564a8c350b244aef4/medical_o1_sft.json",
        "size_bytes": 58177051,
        "checksum": {
          "algorithm": "sha256",
          "value": "6a0289ebe0d07e3e77e8dbc81c31fcfc02cc99c7bca1602694cb2f76d505667e"
        },
        "format": "json"
      },
      {
        "name": "medical_o1_sft_Chinese.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT/resolve/fc2c9e8a37b38f38da6d449564a8c350b244aef4/medical_o1_sft_Chinese.json",
        "size_bytes": 50634791,
        "checksum": {
          "algorithm": "sha256",
          "value": "e64b1426723b63899287236d20e9bbaec9f185e1ce4b24e9b61f610facb4369a"
        },
        "format": "json"
      },
      {
        "name": "medical_o1_sft_mix.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT/resolve/fc2c9e8a37b38f38da6d449564a8c350b244aef4/medical_o1_sft_mix.json",
        "size_bytes": 73100730,
        "checksum": {
          "algorithm": "sha256",
          "value": "4b23f8abe78952862c9f136ab6b0d7e3e57be54322151f8630982b333076de8c"
        },
        "format": "json"
      },
      {
        "name": "medical_o1_sft_mix_Chinese.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT/resolve/fc2c9e8a37b38f38da6d449564a8c350b244aef4/medical_o1_sft_mix_Chinese.json",
        "size_bytes": 65567029,
        "checksum": {
          "algorithm": "sha256",
          "value": "d77cc166fb9a0fe1c2360a1638e2dc784fd1866ce0e0eab7c7cc921dd252c2e6"
        },
        "format": "json"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download FreedomIntelligence/medical-o1-reasoning-SFT --repo-type dataset",
        "evidence": {
          "excerpt": "You can use the hf download command from the terminal to directly download files from the Hub.",
          "doc": "hf-download",
          "url": "https://huggingface.co/docs/huggingface_hub/guides/download",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": "fc2c9e8a37b38f38da6d449564a8c350b244aef4",
      "last_modified": "2025-04-22T15:11:21.000Z"
    },
    "license_note": {
      "license_status": "permissive",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    },
    "gaps": []
  },
  "_links": {
    "text": "Continue in this database. This record is one of 109 processed and verified records (datasets, data resources and open models). To find others, call `https://mcp.mdexa.com/v1/datasets?q=<words>` or connect the MCP server at `https://mcp.mdexa.com/mcp`; no key is needed for 20 calls per minute. Rows are under 1 KB; an empty result means \"not listed\". For a list of items, one batch check (free account) returns a report. Guide: /agents.md. Similar records: Medical-Reasoning-SFT-Mega (https://mdexa.com/datasets/medical-reasoning-sft-mega/); ChatMed_Consult_Dataset (https://mdexa.com/datasets/chatmed-consult-dataset/); HuatuoGPT2-SFT-GPT4-140K (https://mdexa.com/datasets/huatuogpt2-sft-gpt4-140k/).",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=binding%20affinity"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/agents.md",
    "faq": "https://mdexa.com/developers/faq/",
    "similar": [
      {
        "name": "Medical-Reasoning-SFT-Mega",
        "url": "https://mdexa.com/datasets/medical-reasoning-sft-mega/",
        "json": "https://mdexa.com/datasets/medical-reasoning-sft-mega.json"
      },
      {
        "name": "ChatMed_Consult_Dataset",
        "url": "https://mdexa.com/datasets/chatmed-consult-dataset/",
        "json": "https://mdexa.com/datasets/chatmed-consult-dataset.json"
      },
      {
        "name": "HuatuoGPT2-SFT-GPT4-140K",
        "url": "https://mdexa.com/datasets/huatuogpt2-sft-gpt4-140k/",
        "json": "https://mdexa.com/datasets/huatuogpt2-sft-gpt4-140k.json"
      }
    ]
  }
}