{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "huatuo-knowledge-graph-qa",
  "name": "Huatuo_knowledge_graph_qa",
  "summary": {
    "en": "License: permissive (Apache-2.0); Mdexa hosting: link-only. first-hand data-scope statement(s) allow commercial use and redistribution",
    "zh": "许可证声明：宽松（Apache-2.0）；本站处理：只链接原出处。针对数据的声明允许商用和再分发。"
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "qa-dialogue",
    "knowledge-graph"
  ],
  "content_description": {
    "en": "QA dataset built from a medical knowledge map with 798,444 items; questions are template-generated and answers are the contents of knowledge-map entries.",
    "zh": "基于医学知识图谱构建的问答数据集，共798,444条数据，问题由模板生成，答案取自知识图谱条目内容。"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "798,444 pieces of data",
    "measures": []
  },
  "publisher": "FreedomIntelligence",
  "year": {
    "value": 2023,
    "raw": "2023"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "Apache-2.0",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "first-hand data-scope statement(s) allow commercial use and redistribution",
      "zh": "针对数据的声明允许商用和再分发"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "license: apache-2.0",
        "spdx": "Apache-2.0",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_knowledge_graph_qa",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      }
    ],
    "license_conditions": [
      "notice-required"
    ]
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "en": "License permissive: first-hand data-scope statement(s) allow commercial use and redistribution. Link only.",
    "zh": "许可证宽松：针对数据的声明允许商用和再分发。只链接原出处。"
  },
  "signoff": null,
  "risk_flags": [],
  "provenance": {
    "source_description": null,
    "upstream": []
  },
  "known_issues": [],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/FreedomIntelligence/huatuo_knowledge_graph_qa"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": [
      "arXiv:2305.01526"
    ]
  },
  "verification_level": "verified",
  "last_verified": "2026-11-14",
  "tags": [
    {
      "facet": "task_format",
      "value": "open-qa",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "in which the questions are constructed by means of templates, and the answers are the contents of the entries in the knowledge map.",
      "snapshot_id": "s01"
    },
    {
      "facet": "source_type",
      "value": "knowledge-base",
      "basis": "author-stated",
      "excerpt": "the answers are the contents of the entries in the knowledge map.",
      "snapshot_id": "s01"
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "We built this QA dataset based on the medical knowledge map",
      "snapshot_id": "s01"
    }
  ],
  "changelog": [
    {
      "date": "2026-11-14",
      "change": {
        "en": "Added via the automated pipeline and passed all checks (gates, verbatim quotes, rule engine, two independent extractions).",
        "zh": "经自动流水线收录并通过全部校验（门禁、逐字引用、判定引擎、两轮独立抽取）。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "FreedomIntelligence/huatuo_knowledge_graph_qa",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/FreedomIntelligence/huatuo_knowledge_graph_qa",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_knowledge_graph_qa/resolve/b01fb013d5595abe18c97408dd2fc939e4f7ea3f/.gitattributes",
        "size_bytes": 2440,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_knowledge_graph_qa/resolve/b01fb013d5595abe18c97408dd2fc939e4f7ea3f/README.md",
        "size_bytes": 1238,
        "checksum": null,
        "format": "md"
      },
      {
        "name": "my_dataset.py",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_knowledge_graph_qa/resolve/b01fb013d5595abe18c97408dd2fc939e4f7ea3f/my_dataset.py",
        "size_bytes": 2069,
        "checksum": null,
        "format": "py"
      },
      {
        "name": "test_datasets.jsonl",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_knowledge_graph_qa/resolve/b01fb013d5595abe18c97408dd2fc939e4f7ea3f/test_datasets.jsonl",
        "size_bytes": 174081,
        "checksum": {
          "algorithm": "sha256",
          "value": "56d4dc9f0fdf5dd43ee652ea6bd1567d698cf2a9d7b288f00e203a18e0bda82f"
        },
        "format": "jsonl"
      },
      {
        "name": "train_datasets.jsonl",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_knowledge_graph_qa/resolve/b01fb013d5595abe18c97408dd2fc939e4f7ea3f/train_datasets.jsonl",
        "size_bytes": 148347165,
        "checksum": {
          "algorithm": "sha256",
          "value": "7716b46897e2dbef177af91670b2afd1d4989582bc237465a7fc574cc8269c1f"
        },
        "format": "jsonl"
      },
      {
        "name": "validation_datasets.jsonl",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_knowledge_graph_qa/resolve/b01fb013d5595abe18c97408dd2fc939e4f7ea3f/validation_datasets.jsonl",
        "size_bytes": 321211,
        "checksum": {
          "algorithm": "sha256",
          "value": "fd5920e32f7343a31e2501b49b3e4061f703b6fb537e54881905a0a7b5bf8c39"
        },
        "format": "jsonl"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download FreedomIntelligence/huatuo_knowledge_graph_qa --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": "b01fb013d5595abe18c97408dd2fc939e4f7ea3f",
      "last_modified": "2023-07-07T08:46:58.000Z"
    },
    "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: ESL-bench (Event-driven Synthetic Longitudinal Benchmark) (https://mdexa.com/datasets/esl-bench/); ChatMed_Consult_Dataset (https://mdexa.com/datasets/chatmed-consult-dataset/); Chinese-medical-dialogue-data（Toyhom） (https://mdexa.com/datasets/chinese-medical-dialogue-data/).",
    "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": "ESL-bench (Event-driven Synthetic Longitudinal Benchmark)",
        "url": "https://mdexa.com/datasets/esl-bench/",
        "json": "https://mdexa.com/datasets/esl-bench.json"
      },
      {
        "name": "ChatMed_Consult_Dataset",
        "url": "https://mdexa.com/datasets/chatmed-consult-dataset/",
        "json": "https://mdexa.com/datasets/chatmed-consult-dataset.json"
      },
      {
        "name": "Chinese-medical-dialogue-data（Toyhom）",
        "url": "https://mdexa.com/datasets/chinese-medical-dialogue-data/",
        "json": "https://mdexa.com/datasets/chinese-medical-dialogue-data.json"
      }
    ]
  }
}