{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "cblue",
  "name": "CBLUE",
  "summary": {
    "zh": "许可证声明：未声明（NOASSERTION）；本站处理：待确认，暂只链接原出处。许可证未声明许可：只有代码仓库许可证，未声明数据许可；确认前只链接原出处。",
    "en": "License: unstated (NOASSERTION); Mdexa hosting: pending. License unstated: Only a code repository license; no data license stated; link only until resolved."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "benchmark-exam",
    "annotated-corpus"
  ],
  "content_description": {
    "en": "Benchmark (8 Chinese biomedical language understanding tasks)",
    "zh": "评测集（8项中文生物医学语言理解任务）"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "8个任务：CMeEE 23,000、CMeIE 22,406、CHIP-CDN 18,192、CHIP-STS 30,000、CHIP-CTC 40,644、KUAKE-QIC 10,830、KUAKE-QTR 32,552、KUAKE-QQR 18,196（训/验/测合计）",
    "measures": [
      {
        "value": 8,
        "unit": "tasks",
        "qualifier": "exact",
        "scope": "tasks"
      },
      {
        "value": 23000,
        "unit": "items",
        "qualifier": "exact",
        "scope": "CMeEE"
      },
      {
        "value": 22406,
        "unit": "items",
        "qualifier": "exact",
        "scope": "CMeIE"
      },
      {
        "value": 18192,
        "unit": "items",
        "qualifier": "exact",
        "scope": "CHIP-CDN"
      },
      {
        "value": 30000,
        "unit": "items",
        "qualifier": "exact",
        "scope": "CHIP-STS"
      },
      {
        "value": 40644,
        "unit": "items",
        "qualifier": "exact",
        "scope": "CHIP-CTC"
      },
      {
        "value": 10830,
        "unit": "items",
        "qualifier": "exact",
        "scope": "KUAKE-QIC"
      },
      {
        "value": 32552,
        "unit": "items",
        "qualifier": "exact",
        "scope": "KUAKE-QTR"
      },
      {
        "value": 18196,
        "unit": "items",
        "qualifier": "exact",
        "scope": "KUAKE-QQR"
      }
    ]
  },
  "publisher": "中国多家高校与机构（ACL 2022 论文，Ningyu Zhang 等）",
  "year": {
    "value": 2022,
    "raw": "2022"
  },
  "expert_review": {
    "en": "Not stated",
    "zh": "未说明"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "NOASSERTION",
    "commercial_use": "unstated",
    "derivatives": "unstated",
    "redistribution": "unstated",
    "rationale": {
      "en": "Only a code repository license; no data license stated",
      "zh": "只有代码仓库许可证，未声明数据许可"
    },
    "evidence": [
      {
        "location": "repo-license",
        "location_detail": {
          "en": "GitHub repository license: Apache-2.0 (code and data not distinguished)",
          "zh": "GitHub 仓库许可证：Apache-2.0（未区分代码与数据）"
        },
        "excerpt": "Apache License\nVersion 2.0, January 2004",
        "spdx": "Apache-2.0",
        "url": "https://github.com/CBLUEbenchmark/CBLUE",
        "verified_on": "2026-11-12",
        "snapshot_id": "s02",
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "README states no data license; data hosted on Tianchi, download-page terms not opened [Note: No license statement seen in snapshot s01, s02, s03]",
          "zh": "README 未写数据许可；数据托管于天池，下载页条款未打开［备注：快照中未见许可声明（快照 s01, s02, s03）］"
        },
        "excerpt": null,
        "spdx": null,
        "url": "https://github.com/CBLUEbenchmark/CBLUE",
        "verified_on": "2026-11-12",
        "snapshot_id": null,
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "unstated",
  "hosting": "pending",
  "hosting_reason": {
    "zh": "许可证未声明许可：只有代码仓库许可证，未声明数据许可；确认前只链接原出处。",
    "en": "License unstated: Only a code repository license; no data license stated; link only until resolved."
  },
  "signoff": null,
  "repo_license": {
    "spdx": "Apache-2.0",
    "source": "license-file",
    "verified": true,
    "snapshot_id": "s02",
    "url": "https://github.com/CBLUEbenchmark/CBLUE"
  },
  "risk_flags": [],
  "provenance": {
    "source_description": {
      "en": "Real biomedical scenario data (README description)",
      "zh": "真实生物医学场景数据（README 描述）"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "Data is downloaded via Tianchi; the download page terms were not opened this time",
      "zh": "数据通过天池下载，下载页许可条款本次未打开"
    },
    {
      "en": "Code license and data license are not distinguished",
      "zh": "代码许可证与数据许可证未区分"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://github.com/CBLUEbenchmark/CBLUE"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified-no-license-statement",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "task_format",
      "value": "ner",
      "basis": "author-stated",
      "excerpt": "The evaluation task is the recognition of the named entity on the medical text. Given schema data and medical sentences, models are expected to extract entity about cli",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "relation-extraction",
      "basis": "author-stated",
      "excerpt": "| CMeIE     | Relation Extraction     | 14,339 | 3,585 | 4,482  | Micro F1           |",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "term-normalization",
      "basis": "author-stated",
      "excerpt": "The evaluation task is the normalization of the diagnosis entity from the Chinese medical record. Given a diagnosis entity,  models are expected to return corresponding standard terms.",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "text-classification",
      "basis": "author-stated",
      "excerpt": "| CHIP-CTC  | Sentence Classification | 22,962 | 7,682 | 10,000 | Macro F1           |",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "text-matching",
      "basis": "author-stated",
      "excerpt": "| CHIP-STS  | Sentence Similarity     | 16,000 | 4,000 | 10,000 | Macro F1           |",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "We evaluate the current 11 Chinese pre-trained models on the eight biomedical language understanding tasks and report the baselines of these tasks.",
      "snapshot_id": "s01"
    },
    {
      "facet": "official_split",
      "value": "full-split",
      "basis": "author-stated",
      "excerpt": "|  └── {Task}_dev.json",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "json",
      "basis": "author-stated",
      "excerpt": "|  └── {Task}_train.json",
      "snapshot_id": "s01"
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "zh": "综合医学文本任务集，未限定专科",
        "en": "综合医学文本任务集; 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": "2026-11-12",
      "change": {
        "en": "Recorded the code repository license separately; it is not treated as a data license statement.",
        "zh": "单独记录代码仓库许可证，不视为数据许可声明。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 8 (7 stated by the authors with excerpts, 1 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 8 个（作者声明 7 个，附逐字摘录；据内容推断 1 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 the data_format tag (json), based on the file layout of the repository.",
        "zh": "补打 data_format=json 标签，依据仓库的文件目录结构。"
      }
    },
    {
      "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": "github",
    "repo_id": "CBLUEbenchmark/CBLUE",
    "source": {
      "api_url": "https://api.github.com/repos/CBLUEbenchmark/CBLUE",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "git clone https://github.com/CBLUEbenchmark/CBLUE",
        "evidence": {
          "excerpt": "git clone https://github.com/YOUR-USERNAME/YOUR-REPOSITORY",
          "doc": "github-clone",
          "url": "https://docs.github.com/en/repositories/creating-and-managing-repositories/cloning-a-repository",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": null,
      "last_modified": "2023-05-03T15:28:49Z",
      "default_branch": "main"
    },
    "license_note": {
      "license_status": "unstated",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    },
    "gaps": [
      "the platform publishes no checksum for these files; none was computed (we do not download data files)"
    ]
  },
  "_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: PromptCBLUE (https://mdexa.com/datasets/promptcblue/); IMCS-21 (https://mdexa.com/datasets/imcs-21/); PubMedCausal (https://mdexa.com/datasets/pubmedcausal/).",
    "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": "PromptCBLUE",
        "url": "https://mdexa.com/datasets/promptcblue/",
        "json": "https://mdexa.com/datasets/promptcblue.json"
      },
      {
        "name": "IMCS-21",
        "url": "https://mdexa.com/datasets/imcs-21/",
        "json": "https://mdexa.com/datasets/imcs-21.json"
      },
      {
        "name": "PubMedCausal",
        "url": "https://mdexa.com/datasets/pubmedcausal/",
        "json": "https://mdexa.com/datasets/pubmedcausal.json"
      }
    ]
  }
}