{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "traditional-chinese-medicine-dataset-pretrain",
  "name": "Traditional-Chinese-Medicine-Dataset-Pretrain",
  "summary": {
    "en": "License: permissive (Apache-2.0); Mdexa hosting: link-only. first-hand data-scope statement(s) allow commercial use and redistribution Risk flag(s): real-patient-text, scraped.",
    "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。来源风险标记：real-patient-text、scraped。"
  },
  "systems": [
    "traditional-medicine",
    "modern-medicine"
  ],
  "domains": [
    "tcm",
    "tcm-classics",
    "tcm-case-records",
    "tcm-materia-medica",
    "tcm-formulas",
    "tcm-acupuncture-tuina",
    "tcm-diagnostics",
    "clinical-medicine"
  ],
  "content_types": [
    "clinical-cases",
    "classical-texts",
    "database",
    "terminology-coding-system"
  ],
  "content_description": {
    "en": "TCM pretraining corpus from non-Internet internal sources: ~1GB of clinical cases, classics, encyclopedias and terminology entries, 99% Simplified Chinese; for pretraining only.",
    "zh": "非网络来源的高质量中医预训练数据集，约1GB，涵盖临床案例、名家典籍、医学百科、名词解释等，99%为简体中文，仅用于预训练。"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "约1GB",
    "measures": []
  },
  "publisher": "SylvanL",
  "year": {
    "value": null,
    "raw": null
  },
  "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/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "注意：该数据集仅适用于预训练或继续预训练用途，针对SFT/IFT的QA数据集详见：SylvanL/Traditional-Chinese-Medicine-Dataset-SFT",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      }
    ],
    "license_conditions": [
      "notice-required"
    ],
    "notes": {
      "en": "risk flag(s) real-patient-text,scraped: never eligible or hosted",
      "zh": "risk flag(s) real-patient-text,scraped: never eligible or hosted"
    }
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "en": "License permissive: first-hand data-scope statement(s) allow commercial use and redistribution. Risk flag(s): real-patient-text, scraped. Link only.",
    "zh": "许可证宽松：针对数据的声明允许商用和再分发。来源风险标记：real-patient-text、scraped。只链接原出处。"
  },
  "signoff": null,
  "risk_flags": [
    "real-patient-text",
    "scraped"
  ],
  "provenance": {
    "source_description": null,
    "upstream": []
  },
  "known_issues": [
    {
      "en": "The 230,000-record EMR-derived portion is assembled by rule-based table joining and the authors describe its quality as only moderate.",
      "zh": "23万条EMR医案由规则联表拼接，作者自评质量中规中矩。"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": []
  },
  "verification_level": "verified",
  "last_verified": "2026-11-14",
  "tags": [
    {
      "facet": "intended_use",
      "value": "pretraining",
      "basis": "author-stated",
      "excerpt": "注意：该数据集仅适用于预训练或继续预训练用途，针对SFT/IFT的QA数据集详见：SylvanL/Traditional-Chinese-Medicine-Dataset-SFT",
      "snapshot_id": "s01"
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "author-stated",
      "excerpt": "包含约1GB的中医各个领域临床案例、名家典籍、医学百科，名词解释等优质内容，涵盖全面，配比均衡。",
      "snapshot_id": "s01"
    },
    {
      "facet": "source_type",
      "value": "classical-text",
      "basis": "author-stated",
      "excerpt": "包含来自688本中医领域常用教材、著作、典籍的146244条书本内容。",
      "snapshot_id": "s01"
    },
    {
      "facet": "source_type",
      "value": "textbook-reference",
      "basis": "author-stated",
      "excerpt": "包含来自688本中医领域常用教材、著作、典籍的146244条书本内容。",
      "snapshot_id": "s01"
    },
    {
      "facet": "source_type",
      "value": "knowledge-base",
      "basis": "author-stated",
      "excerpt": "涵盖疾病、症状、医疗美容、药品、中药材、保健品、方剂、药膳食疗、针灸穴位、术语等的百科词条",
      "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）。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/.gitattributes",
        "size_bytes": 3368,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "CPT_medicalRecord_source1_61486.json",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/CPT_medicalRecord_source1_61486.json",
        "size_bytes": 99557544,
        "checksum": {
          "algorithm": "sha256",
          "value": "4e43ac20d8063de20f61773473480fa248525781092d8d02008f5741e8f43f38"
        },
        "format": "json"
      },
      {
        "name": "CPT_medicalRecord_source2_15307.json",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/CPT_medicalRecord_source2_15307.json",
        "size_bytes": 15747842,
        "checksum": {
          "algorithm": "sha256",
          "value": "8d1a83f65d0cd27f7727d9c1e793560da87a3d10f6aa50af104fa3ec86efe4f5"
        },
        "format": "json"
      },
      {
        "name": "CPT_medicalRecord_source3_230000.json",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/CPT_medicalRecord_source3_230000.json",
        "size_bytes": 115166171,
        "checksum": {
          "algorithm": "sha256",
          "value": "a6a3cf4d696fb3307afdfd0918341d13c49ad83db307c1e3390e5f488feadbf4"
        },
        "format": "json"
      },
      {
        "name": "CPT_medicalRecord_source4_48665.json",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/CPT_medicalRecord_source4_48665.json",
        "size_bytes": 37165644,
        "checksum": {
          "algorithm": "sha256",
          "value": "337b89722abb775814aff4fd77698b6a0280115773407ac1a7f86b30c678b8c2"
        },
        "format": "json"
      },
      {
        "name": "CPT_tcmBooks_source1_146244.json",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/CPT_tcmBooks_source1_146244.json",
        "size_bytes": 243373664,
        "checksum": {
          "algorithm": "sha256",
          "value": "81714c013a09ffcbc7a32bcdf1b6a9dc22772d0c2485f9b77598c3f8c98c713c"
        },
        "format": "json"
      },
      {
        "name": "CPT_tcmKnowledge_source1_17921.json",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/CPT_tcmKnowledge_source1_17921.json",
        "size_bytes": 10884409,
        "checksum": {
          "algorithm": "sha256",
          "value": "5ea806912de0bc24f8b1fc8adb65f219191903938116169b7b2e00f45d001880"
        },
        "format": "json"
      },
      {
        "name": "CPT_tcmKnowledge_source2_12889.json",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/CPT_tcmKnowledge_source2_12889.json",
        "size_bytes": 53293015,
        "checksum": {
          "algorithm": "sha256",
          "value": "fd88c8db6598e888319a6c79c3374b926420b64a359f708ad6a9005cb5b6051d"
        },
        "format": "json"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/README.md",
        "size_bytes": 41934,
        "checksum": null,
        "format": "md"
      },
      {
        "name": "dataset_info.json",
        "url": "https://huggingface.co/datasets/SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain/resolve/fd01649d8e019ed2b002119e0fd74076c5f7b73d/dataset_info.json",
        "size_bytes": 1022,
        "checksum": null,
        "format": "json"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download SylvanL/Traditional-Chinese-Medicine-Dataset-Pretrain --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": "fd01649d8e019ed2b002119e0fd74076c5f7b73d",
      "last_modified": "2026-08-02T11:49:04.000Z"
    },
    "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": "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：LingLanMedBench Traditional Chinese Medicine Benchmark Dataset (https://mdexa.com/zh/datasets/linglan/)；Traditional Chinese Medicine Examination (https://mdexa.com/zh/datasets/tcmle/)；TCM-Vision-Benchmark (https://mdexa.com/zh/datasets/tcm-vision-benchmark/)。",
    "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": "LingLanMedBench Traditional Chinese Medicine Benchmark Dataset",
        "url": "https://mdexa.com/zh/datasets/linglan/",
        "json": "https://mdexa.com/zh/datasets/linglan.json"
      },
      {
        "name": "Traditional Chinese Medicine Examination",
        "url": "https://mdexa.com/zh/datasets/tcmle/",
        "json": "https://mdexa.com/zh/datasets/tcmle.json"
      },
      {
        "name": "TCM-Vision-Benchmark",
        "url": "https://mdexa.com/zh/datasets/tcm-vision-benchmark/",
        "json": "https://mdexa.com/zh/datasets/tcm-vision-benchmark.json"
      }
    ]
  }
}