{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "promptcblue",
  "name": "PromptCBLUE",
  "summary": {
    "zh": "许可证声明：有限制（NOASSERTION）；本站处理：只链接原出处。许可证有限制：README 写明严禁商用；只链接原出处。",
    "en": "License: restricted (NOASSERTION); Mdexa hosting: link-only. License is restricted: README prohibits commercial use; link only."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "benchmark-exam",
    "annotated-corpus"
  ],
  "content_description": {
    "en": "Benchmark (prompt-formatted multi-task version of CBLUE)",
    "zh": "评测集（CBLUE 的提示词化多任务）"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "v0.2：训练68,900、验证10,360、Test A 10,320、Test B 10,320；94个提示模板",
    "measures": [
      {
        "value": 68900,
        "unit": "items",
        "qualifier": "exact",
        "scope": "v0.2 train"
      },
      {
        "value": 10360,
        "unit": "items",
        "qualifier": "exact",
        "scope": "v0.2 validation"
      },
      {
        "value": 10320,
        "unit": "items",
        "qualifier": "exact",
        "scope": "v0.2 Test A"
      },
      {
        "value": 10320,
        "unit": "items",
        "qualifier": "exact",
        "scope": "v0.2 Test B"
      },
      {
        "value": 94,
        "unit": "items",
        "qualifier": "exact",
        "scope": "prompt templates"
      }
    ]
  },
  "publisher": "michael-wzhu 等（CCKS/天池评测）",
  "year": {
    "value": 2023,
    "raw": "2023"
  },
  "expert_review": {
    "en": "Not stated",
    "zh": "未说明"
  },
  "license": {
    "legacy_status": "index-only",
    "spdx": "NOASSERTION",
    "commercial_use": "no",
    "derivatives": "unstated",
    "redistribution": "unstated",
    "rationale": {
      "en": "README prohibits commercial use",
      "zh": "README 写明严禁商用"
    },
    "evidence": [
      {
        "location": "repo-sidebar",
        "location_detail": {
          "en": "Repository page shows no license [Note: No license statement seen in snapshot s01, s02]",
          "zh": "仓库页面未写许可证［备注：快照中未见许可声明（快照 s01, s02）］"
        },
        "excerpt": null,
        "spdx": null,
        "url": "https://github.com/michael-wzhu/PromptCBLUE",
        "verified_on": "2026-11-12",
        "snapshot_id": null,
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "README non-commercial statement",
          "zh": "README 非商用声明"
        },
        "excerpt": "本项目相关资源仅供学术研究之用，严禁用于商业用途。",
        "spdx": null,
        "url": "https://github.com/michael-wzhu/PromptCBLUE",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "restricted",
  "hosting": "link-only",
  "hosting_reason": {
    "zh": "许可证有限制：README 写明严禁商用；只链接原出处。",
    "en": "License is restricted: README prohibits commercial use; link only."
  },
  "signoff": null,
  "risk_flags": [
    "derived"
  ],
  "provenance": {
    "source_description": {
      "en": "CBLUE tasks rewritten into prompt format",
      "zh": "由 CBLUE 各任务改写为提示格式"
    },
    "upstream": [
      {
        "slug": "cblue",
        "name": "CBLUE",
        "relation": "derived-from"
      }
    ]
  },
  "known_issues": [
    {
      "en": "Underlying data comes from CBLUE; CBLUE data terms must be checked as well",
      "zh": "底层数据来自 CBLUE，需同时核对 CBLUE 数据条款"
    },
    {
      "en": "Competition rules forbid calling public model APIs directly to predict the test set",
      "zh": "比赛规则禁止直接调用公开模型 API 预测测试集"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://github.com/michael-wzhu/PromptCBLUE"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified-no-license-statement",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "s://tianchi.aliyun.com/dataset/95414)基准进行二次开发，将16种不同的医疗场景NLP任务全部转化为基于提示的语言生成任务,形成首个中文医疗场景的LLM评测基准。**PromptCBLUE**作为CCKS-2023的评测任务之一，已在阿里巴巴天池大赛平台上线进行开放评测，欢迎各位师生报名参赛(刷榜)。",
      "snapshot_id": "s01"
    },
    {
      "facet": "benchmark_status",
      "value": "public-leaderboard",
      "basis": "author-stated",
      "excerpt": "- 在CCKS-2023会议后，PromptCBLUE将作为天池数据集，长期开放榜单，供社区评测/打榜。",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "jsonl",
      "basis": "author-stated",
      "excerpt": "PromptCBLUE中将各个任务都已经转化为了根据prompt生成回复的统一格式，测试样本在[test.json](./datasets/toy_examples/test.json)文件中，这个文件采用json line格式，每行是一个可json化的字符串，json化后\"input\"字段作为LLM输入，\"target\"字段为空字符串，待选手们填入模型回复。",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "ner",
      "basis": "inferred",
      "inferred_from": "upstream-dataset",
      "note": {
        "en": "Upstream CBLUE has NER.",
        "zh": "上游 CBLUE 含实体识别"
      }
    },
    {
      "facet": "task_format",
      "value": "relation-extraction",
      "basis": "inferred",
      "inferred_from": "upstream-dataset",
      "note": {
        "en": "Upstream CBLUE has RE.",
        "zh": "上游 CBLUE 含关系抽取"
      }
    },
    {
      "facet": "task_format",
      "value": "term-normalization",
      "basis": "inferred",
      "inferred_from": "upstream-dataset",
      "note": {
        "en": "Upstream CBLUE has normalization.",
        "zh": "上游 CBLUE 含术语标准化"
      }
    },
    {
      "facet": "task_format",
      "value": "text-classification",
      "basis": "inferred",
      "inferred_from": "upstream-dataset",
      "note": {
        "en": "Upstream CBLUE has classification.",
        "zh": "上游 CBLUE 含分类"
      }
    },
    {
      "facet": "official_split",
      "value": "full-split",
      "basis": "inferred",
      "inferred_from": "card-size",
      "note": {
        "en": "Card size lists train/dev/test.",
        "zh": "卡片规模含训练/验证/测试"
      }
    },
    {
      "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": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 9 (3 stated by the authors with excerpts, 6 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 9 个（作者声明 3 个，附逐字摘录；据内容推断 6 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": "github",
    "repo_id": "michael-wzhu/PromptCBLUE",
    "source": {
      "api_url": "https://api.github.com/repos/michael-wzhu/PromptCBLUE",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "git clone https://github.com/michael-wzhu/PromptCBLUE",
        "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": "2024-01-23T13:53:41Z",
      "default_branch": "main"
    },
    "license_note": {
      "license_status": "restricted",
      "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": "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：CBLUE (https://mdexa.com/zh/datasets/cblue/)；PMC-Patients-ReCDS (https://mdexa.com/zh/datasets/pmc-patients-recds/)；CMB (Chinese Medical Benchmark) (https://mdexa.com/zh/datasets/cmb/)。",
    "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": "CBLUE",
        "url": "https://mdexa.com/zh/datasets/cblue/",
        "json": "https://mdexa.com/zh/datasets/cblue.json"
      },
      {
        "name": "PMC-Patients-ReCDS",
        "url": "https://mdexa.com/zh/datasets/pmc-patients-recds/",
        "json": "https://mdexa.com/zh/datasets/pmc-patients-recds.json"
      },
      {
        "name": "CMB (Chinese Medical Benchmark)",
        "url": "https://mdexa.com/zh/datasets/cmb/",
        "json": "https://mdexa.com/zh/datasets/cmb.json"
      }
    ]
  }
}