{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "chatmed-consult-dataset",
  "name": "ChatMed_Consult_Dataset",
  "summary": {
    "zh": "许可证声明：各处冲突（NOASSERTION）；本站处理：待确认，暂只链接原出处。许可证各处声明冲突：HF 元数据 CC BY 4.0 与卡片正文 CC BY-NC 4.0 冲突；确认前只链接原出处。",
    "en": "License: conflict (NOASSERTION); Mdexa hosting: pending. License conflict: HF metadata CC BY 4.0 conflicts with card text CC BY-NC 4.0; link only until resolved."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "qa-dialogue"
  ],
  "content_description": {
    "en": "Consultation QA (answers generated by ChatGPT)",
    "zh": "问诊问答（ChatGPT 生成回答）"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "HF 行数549,326；卡片文字称110,113对（不一致）",
    "measures": [
      {
        "value": 549326,
        "unit": "rows",
        "qualifier": "exact",
        "scope": "HF rows"
      },
      {
        "value": 110113,
        "unit": "qa-pairs",
        "qualifier": "claimed",
        "scope": "card text (inconsistent)"
      }
    ]
  },
  "publisher": "michaelwzhu（ChatMed）",
  "year": {
    "value": null,
    "raw": "未标明（项目2023）"
  },
  "expert_review": {
    "en": "Not written by physicians",
    "zh": "非医生撰写"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "NOASSERTION",
    "commercial_use": "conflict",
    "derivatives": "unstated",
    "redistribution": "unstated",
    "rationale": {
      "en": "HF metadata CC BY 4.0 conflicts with card text CC BY-NC 4.0",
      "zh": "HF 元数据 CC BY 4.0 与卡片正文 CC BY-NC 4.0 冲突"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "HF metadata: cc-by-4.0",
          "zh": "HF 元数据：cc-by-4.0"
        },
        "excerpt": "license: cc-by-4.0",
        "spdx": "CC-BY-4.0",
        "url": "https://huggingface.co/datasets/michaelwzhu/ChatMed_Consult_Dataset",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "hf-card-text",
        "location_detail": {
          "en": "Card Licensing Information: CC BY-NC 4.0",
          "zh": "卡片 Licensing Information：CC BY-NC 4.0"
        },
        "excerpt": "The dataset is available under the Creative Commons NonCommercial (CC BY-NC 4.0) .",
        "spdx": "CC-BY-NC-4.0",
        "url": "https://huggingface.co/datasets/michaelwzhu/ChatMed_Consult_Dataset",
        "verified_on": "2026-11-12",
        "snapshot_id": "s02",
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "conflict",
  "hosting": "pending",
  "hosting_reason": {
    "zh": "许可证各处声明冲突：HF 元数据 CC BY 4.0 与卡片正文 CC BY-NC 4.0 冲突；确认前只链接原出处。",
    "en": "License conflict: HF metadata CC BY 4.0 conflicts with card text CC BY-NC 4.0; link only until resolved."
  },
  "signoff": null,
  "risk_flags": [
    "scraped",
    "model-generated"
  ],
  "provenance": {
    "source_description": {
      "en": "User questions scraped from an online medical consultation website; answers generated by GPT-3.5",
      "zh": "用户问题爬取自在线医疗咨询网站，回答由 GPT-3.5 生成"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "Metadata license conflicts with the card text",
      "zh": "元数据与卡片许可证冲突"
    },
    {
      "en": "The card says it may contain errors and bias",
      "zh": "卡片称可能含错误与偏见"
    },
    {
      "en": "Answers are GPT-3.5 output",
      "zh": "回答为 GPT-3.5 输出"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/michaelwzhu/ChatMed_Consult_Dataset"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "intended_use",
      "value": "fine-tuning",
      "basis": "author-stated",
      "excerpt": "The ChatMed-Dataset designed for fine-tuning pretrained language models to perform better in automatic medical consultations.",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "jsonl",
      "basis": "author-stated",
      "excerpt": "The dataset is in json-line format and is very convenient to use! An example in the ChatMed-Dataset looks as follows:",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "open-qa",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Single-turn consultation QA.",
        "zh": "单轮问诊问答"
      }
    },
    {
      "facet": "expert_involvement",
      "value": "none",
      "basis": "inferred",
      "inferred_from": "card-source",
      "note": {
        "en": "Answers are model output; no review recorded.",
        "zh": "回答由模型生成，卡片未见专家审核"
      }
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "zh": "综合在线问诊问答，未限定专科",
        "en": "综合在线问诊问答; 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: 5 (2 stated by the authors with excerpts, 3 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 5 个（作者声明 2 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": "michaelwzhu/ChatMed_Consult_Dataset",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/michaelwzhu/ChatMed_Consult_Dataset",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/michaelwzhu/ChatMed_Consult_Dataset/resolve/e9d27b6c92ff793d1d060acd85b956cc20350b85/.gitattributes",
        "size_bytes": 2327,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "ChatMed_Consult-v0.3.json",
        "url": "https://huggingface.co/datasets/michaelwzhu/ChatMed_Consult_Dataset/resolve/e9d27b6c92ff793d1d060acd85b956cc20350b85/ChatMed_Consult-v0.3.json",
        "size_bytes": 394547009,
        "checksum": {
          "algorithm": "sha256",
          "value": "0d1e2c3dd12a6cb62644c798fada41a7cc936a4663dea320f62a3dd8debd53f7"
        },
        "format": "json"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/michaelwzhu/ChatMed_Consult_Dataset/resolve/e9d27b6c92ff793d1d060acd85b956cc20350b85/README.md",
        "size_bytes": 4943,
        "checksum": null,
        "format": "md"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download michaelwzhu/ChatMed_Consult_Dataset --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": "e9d27b6c92ff793d1d060acd85b956cc20350b85",
      "last_modified": "2023-05-05T13:41:10.000Z"
    },
    "license_note": {
      "license_status": "conflict",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    },
    "gaps": []
  },
  "_links": {
    "text": "在本库继续查找。本条目是 109 条已处理并核实的记录之一（数据集、数据资源与开源模型）。查找其他条目：调用 `https://mcp.mdexa.com/v1/datasets?q=<关键词>`，或连接 MCP 服务 `https://mcp.mdexa.com/mcp`；每分钟 20 次以内无需密钥。每行返回不到 1 KB；空结果即\"数据库未收录\"。核对一份清单：一次批量核对（免费账号）即返回报告。说明：/agents.md。相似条目：medical-o1-reasoning-SFT（中文子集） (https://mdexa.com/zh/datasets/medical-o1-reasoning-sft/)；Chinese-medical-dialogue-data（Toyhom） (https://mdexa.com/zh/datasets/chinese-medical-dialogue-data/)；DISC-Med-SFT (https://mdexa.com/zh/datasets/disc-med-sft/)。",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=%E7%BB%93%E5%90%88%E4%BA%B2%E5%92%8C%E5%8A%9B"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/zh/agents.md",
    "faq": "https://mdexa.com/zh/developers/faq/",
    "similar": [
      {
        "name": "medical-o1-reasoning-SFT（中文子集）",
        "url": "https://mdexa.com/zh/datasets/medical-o1-reasoning-sft/",
        "json": "https://mdexa.com/zh/datasets/medical-o1-reasoning-sft.json"
      },
      {
        "name": "Chinese-medical-dialogue-data（Toyhom）",
        "url": "https://mdexa.com/zh/datasets/chinese-medical-dialogue-data/",
        "json": "https://mdexa.com/zh/datasets/chinese-medical-dialogue-data.json"
      },
      {
        "name": "DISC-Med-SFT",
        "url": "https://mdexa.com/zh/datasets/disc-med-sft/",
        "json": "https://mdexa.com/zh/datasets/disc-med-sft.json"
      }
    ]
  }
}