{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "tcm-sd",
  "name": "TCM-SD（辨证分型数据集）",
  "summary": {
    "zh": "许可证声明：无法核实（NOASSERTION）；本站处理：待确认，暂只链接原出处。许可证无法核实：只知论文许可，未找到数据许可；确认前只链接原出处。",
    "en": "License: unverifiable (NOASSERTION); Mdexa hosting: pending. License unverifiable: Only the paper license is known; data license not found; link only until resolved."
  },
  "systems": [
    "traditional-medicine"
  ],
  "domains": [
    "tcm-disease-pattern"
  ],
  "content_types": [
    "clinical-cases"
  ],
  "content_description": {
    "en": "Pattern-differentiation case records (real clinical records)",
    "zh": "辨证分型病例（真实临床记录）"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "54,152条真实临床记录，148个证型",
    "measures": [
      {
        "value": 54152,
        "unit": "records",
        "qualifier": "exact",
        "scope": "real clinical records"
      },
      {
        "value": 148,
        "unit": "categories",
        "qualifier": "exact",
        "scope": "patterns"
      }
    ]
  },
  "publisher": "Mucheng Ren 等（CCL 2022，arXiv 2203.10839）",
  "year": {
    "value": 2022,
    "raw": "2022"
  },
  "expert_review": {
    "en": "Not stated",
    "zh": "未说明"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "NOASSERTION",
    "commercial_use": "unverified",
    "derivatives": "unverified",
    "redistribution": "unverified",
    "rationale": {
      "en": "Only the paper license is known; data license not found",
      "zh": "只知论文许可，未找到数据许可"
    },
    "evidence": [
      {
        "location": "paper",
        "location_detail": {
          "en": "arXiv page shows the paper under CC BY-NC-ND 4.0; no data download page or data license found [Note: No license statement seen in snapshot s01]",
          "zh": "arXiv 页面显示论文 CC BY-NC-ND 4.0；未找到数据下载页或数据许可［备注：快照中未见许可声明（快照 s01）］"
        },
        "excerpt": null,
        "spdx": "CC-BY-NC-ND-4.0",
        "url": "https://arxiv.org/abs/2203.10839",
        "verified_on": "2026-11-12",
        "snapshot_id": null,
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "secondary-source",
        "location_detail": {
          "en": "A third-party aggregator says the license is also CC BY-NC-ND; not seen on the original page [Note: No URL recorded, so no snapshot exists]",
          "zh": "第三方聚合站称许可证同为 CC BY-NC-ND，原页未见［备注：未记录网址，无快照］"
        },
        "excerpt": null,
        "spdx": "CC-BY-NC-ND-4.0",
        "url": null,
        "verified_on": null,
        "snapshot_id": null,
        "observed": "secondary-source",
        "secondhand": true
      }
    ]
  },
  "license_status": "unverifiable",
  "hosting": "pending",
  "hosting_reason": {
    "zh": "许可证无法核实：只知论文许可，未找到数据许可；确认前只链接原出处。",
    "en": "License unverifiable: Only the paper license is known; data license not found; link only until resolved."
  },
  "signoff": null,
  "risk_flags": [
    "real-patient-text"
  ],
  "provenance": {
    "source_description": {
      "en": "Real clinical records",
      "zh": "真实临床记录"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "The arXiv page does not link the data",
      "zh": "arXiv 页面未链接数据"
    },
    {
      "en": "A third-party aggregator says the license is also CC BY-NC-ND; not seen on the original page",
      "zh": "第三方聚合站称许可证同为 CC BY-NC-ND，原页未见"
    },
    {
      "en": "Contains clinical records; privacy authorization needs checking",
      "zh": "含临床记录，需核对隐私授权"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://arxiv.org/abs/2203.10839"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": [
      "arXiv:2203.10839"
    ]
  },
  "verification_level": "partially-verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "Title: TCM-SD: A Benchmark for Probing Syndrome Differentiation via Natural Language Processing",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "text-classification",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Classification into 148 patterns.",
        "zh": "148 个证型分类"
      }
    }
  ],
  "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: 3 (1 stated by the authors with excerpts, 2 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 3 个（作者声明 1 个，附逐字摘录；据内容推断 2 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: none (no basis).",
        "zh": "新增专科标签：none (no basis)。"
      }
    }
  ],
  "_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: TCMEval-SDT（辨证思维评测） (https://mdexa.com/datasets/tcmeval-sdt/); CMB (Chinese Medical Benchmark) (https://mdexa.com/datasets/cmb/); DiagnosisArena (https://mdexa.com/datasets/diagnosisarena/).",
    "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": "TCMEval-SDT（辨证思维评测）",
        "url": "https://mdexa.com/datasets/tcmeval-sdt/",
        "json": "https://mdexa.com/datasets/tcmeval-sdt.json"
      },
      {
        "name": "CMB (Chinese Medical Benchmark)",
        "url": "https://mdexa.com/datasets/cmb/",
        "json": "https://mdexa.com/datasets/cmb.json"
      },
      {
        "name": "DiagnosisArena",
        "url": "https://mdexa.com/datasets/diagnosisarena/",
        "json": "https://mdexa.com/datasets/diagnosisarena.json"
      }
    ]
  }
}