{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "cmexam",
  "name": "CMExam",
  "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：官方 README 限定仅限学术研究、禁止商业滥用；非官方镜像卡不算数；只链接原出处。",
    "en": "License: restricted (NOASSERTION); Mdexa hosting: link-only. License is restricted: The official README restricts use to academic research and prohibits commercial misuse; the unofficial mirror card does not count; link only."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "benchmark-exam"
  ],
  "content_description": {
    "en": "Question bank and benchmark (multiple-choice questions with explanations)",
    "zh": "题库与评测集（选择题含解析）"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "68,119题（训练54,497/验证6,811/测试6,811），含解析及五类标注",
    "measures": [
      {
        "value": 68119,
        "unit": "questions",
        "qualifier": "exact",
        "scope": "total"
      },
      {
        "value": 54497,
        "unit": "questions",
        "qualifier": "exact",
        "scope": "train"
      },
      {
        "value": 6811,
        "unit": "questions",
        "qualifier": "exact",
        "scope": "validation"
      },
      {
        "value": 6811,
        "unit": "questions",
        "qualifier": "exact",
        "scope": "test"
      }
    ]
  },
  "publisher": "williamliujl（NeurIPS 2023 论文作者）",
  "year": {
    "value": 2023,
    "raw": "2023"
  },
  "expert_review": {
    "en": "Explanations and annotations described in the paper; the page does not state any review",
    "zh": "解析与标注见论文；页面未说明审核"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "NOASSERTION",
    "commercial_use": "no",
    "derivatives": "unstated",
    "redistribution": "unstated",
    "rationale": {
      "en": "The official README restricts use to academic research and prohibits commercial misuse; the unofficial mirror card does not count",
      "zh": "官方 README 限定仅限学术研究、禁止商业滥用；非官方镜像卡不算数"
    },
    "evidence": [
      {
        "location": "repo-license",
        "location_detail": {
          "en": "GitHub repository license: Apache-2.0",
          "zh": "GitHub 仓库许可证：Apache-2.0"
        },
        "excerpt": "Apache License\nVersion 2.0, January 2004",
        "spdx": "Apache-2.0",
        "url": "https://github.com/williamliujl/cmexam",
        "verified_on": "2026-11-12",
        "snapshot_id": "s04",
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "README academic-use restriction",
          "zh": "README 学术限定声明"
        },
        "excerpt": "Intended for academic/research use only; commercial misuse prohibited.",
        "spdx": null,
        "url": "https://github.com/williamliujl/cmexam",
        "verified_on": "2026-11-12",
        "snapshot_id": "s03",
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Unofficial Hugging Face mirror card: Apache-2.0; the card also says academic research only",
          "zh": "Hugging Face 非官方镜像卡：Apache-2.0；卡片同样写明仅限学术研究"
        },
        "excerpt": "license: apache-2.0",
        "spdx": "Apache-2.0",
        "url": "https://huggingface.co/datasets/fzkuji/CMExam",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "secondhand": true
      }
    ]
  },
  "license_status": "restricted",
  "hosting": "link-only",
  "hosting_reason": {
    "zh": "许可证有限制：官方 README 限定仅限学术研究、禁止商业滥用；非官方镜像卡不算数；只链接原出处。",
    "en": "License is restricted: The official README restricts use to academic research and prohibits commercial misuse; the unofficial mirror card does not count; link only."
  },
  "signoff": null,
  "repo_license": {
    "spdx": "Apache-2.0",
    "source": "license-file",
    "verified": true,
    "snapshot_id": "s04",
    "url": "https://github.com/williamliujl/cmexam"
  },
  "risk_flags": [
    "exam-derived"
  ],
  "provenance": {
    "source_description": {
      "en": "National Medical Licensing Examination",
      "zh": "国家医师资格考试"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "The code repository license is Apache-2.0, coexisting with the README restriction",
      "zh": "代码仓库许可证为 Apache-2.0，与 README 的限制并存"
    },
    {
      "en": "The HF version is an unofficial preprocessed copy; its card also says academic research only",
      "zh": "HF 版本为非官方预处理副本，卡片同样写明仅限学术研究"
    },
    {
      "en": "Sources include national medical licensing exam questions; in August 2026 the National Medical Examination Center issued a statement asserting copyright over past exam questions, so there is a source copyright risk",
      "zh": "来源含国家医学考试题，国家医学考试中心2026年8月声明主张历年试题著作权，存在来源版权风险"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://github.com/williamliujl/cmexam",
      "https://huggingface.co/datasets/fzkuji/CMExam"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "annotation_depth",
      "value": "with-explanation",
      "basis": "author-stated",
      "excerpt": "\\*Q: Question; A: Answer; E: Explanation",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "- Authenticated and accurate for evaluating LLMs.",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "choice-question",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Card: multiple-choice questions.",
        "zh": "卡片内容为选择题"
      }
    },
    {
      "facet": "official_split",
      "value": "full-split",
      "basis": "inferred",
      "inferred_from": "card-size",
      "note": {
        "en": "Card size lists train/val/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": "执业医师考试题库，未限定专科",
        "en": "执业医师考试题库; 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": "2026-11-12",
      "change": {
        "en": "License status changed from conflict to restricted: restrictions are read broadly (official README restriction applies to the data); third-party mirror pages are secondhand.",
        "zh": "许可状态由冲突改为受限：限制从宽认定（官方 README 限制对数据有效）；第三方镜像页记为二手。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 5 (2 stated by the authors with excerpts, 3 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 5 个（作者声明 2 个，附逐字摘录；据内容推断 3 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": "huggingface",
    "repo_id": "fzkuji/CMExam",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/fzkuji/CMExam",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/fzkuji/CMExam/resolve/a4aaeb2d9bc021bb358f45803776f5fe6a06ebe9/.gitattributes",
        "size_bytes": 2512,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/fzkuji/CMExam/resolve/a4aaeb2d9bc021bb358f45803776f5fe6a06ebe9/README.md",
        "size_bytes": 4678,
        "checksum": null,
        "format": "md"
      },
      {
        "name": "cmexam_dataloading.ipynb",
        "url": "https://huggingface.co/datasets/fzkuji/CMExam/resolve/a4aaeb2d9bc021bb358f45803776f5fe6a06ebe9/cmexam_dataloading.ipynb",
        "size_bytes": 7267,
        "checksum": null,
        "format": "ipynb"
      },
      {
        "name": "cmexam_preprocessing.ipynb",
        "url": "https://huggingface.co/datasets/fzkuji/CMExam/resolve/a4aaeb2d9bc021bb358f45803776f5fe6a06ebe9/cmexam_preprocessing.ipynb",
        "size_bytes": 2579,
        "checksum": null,
        "format": "ipynb"
      },
      {
        "name": "test.json",
        "url": "https://huggingface.co/datasets/fzkuji/CMExam/resolve/a4aaeb2d9bc021bb358f45803776f5fe6a06ebe9/test.json",
        "size_bytes": 6434215,
        "checksum": {
          "algorithm": "sha256",
          "value": "f618d52d8ca700471a86202d6b3c8e2ae6505f48e9bd290f63589b4a3ce1f74b"
        },
        "format": "json"
      },
      {
        "name": "train.json",
        "url": "https://huggingface.co/datasets/fzkuji/CMExam/resolve/a4aaeb2d9bc021bb358f45803776f5fe6a06ebe9/train.json",
        "size_bytes": 48807760,
        "checksum": {
          "algorithm": "sha256",
          "value": "4d5b2bccdb234b44109b776779e5999ffee31b14d28f615f1825fcea48cad77e"
        },
        "format": "json"
      },
      {
        "name": "valid.json",
        "url": "https://huggingface.co/datasets/fzkuji/CMExam/resolve/a4aaeb2d9bc021bb358f45803776f5fe6a06ebe9/valid.json",
        "size_bytes": 6154790,
        "checksum": null,
        "format": "json"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download fzkuji/CMExam --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": "a4aaeb2d9bc021bb358f45803776f5fe6a06ebe9",
      "last_modified": "2024-11-02T04:15:45.000Z"
    },
    "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": []
  },
  "_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：CMB (Chinese Medical Benchmark) (https://mdexa.com/zh/datasets/cmb/)；MedMCQA (https://mdexa.com/zh/datasets/medmcqa/)；医学考试题库 JSON 数据集 (https://mdexa.com/zh/datasets/medical-exam-question-bank-json/)。",
    "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": "CMB (Chinese Medical Benchmark)",
        "url": "https://mdexa.com/zh/datasets/cmb/",
        "json": "https://mdexa.com/zh/datasets/cmb.json"
      },
      {
        "name": "MedMCQA",
        "url": "https://mdexa.com/zh/datasets/medmcqa/",
        "json": "https://mdexa.com/zh/datasets/medmcqa.json"
      },
      {
        "name": "医学考试题库 JSON 数据集",
        "url": "https://mdexa.com/zh/datasets/medical-exam-question-bank-json/",
        "json": "https://mdexa.com/zh/datasets/medical-exam-question-bank-json.json"
      }
    ]
  }
}