{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "medqa",
  "name": "MedQA（含大陆中文题，MCMLE）",
  "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：仅仓库层面 MIT，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: Repository-level MIT only; no data license stated; link only until resolved."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "benchmark-exam"
  ],
  "content_description": {
    "en": "Question bank and benchmark (multiple-choice)",
    "zh": "题库与评测集（选择题）"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "页面未列出规模；含简体中文教材及大陆四选项题",
    "measures": []
  },
  "publisher": "jind11（论文作者，arXiv 2009.13081）",
  "year": {
    "value": 2020,
    "raw": "2020"
  },
  "expert_review": {
    "en": "Not stated",
    "zh": "未说明"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "NOASSERTION",
    "commercial_use": "conditional",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "Repository-level MIT only; no data license stated",
      "zh": "仅仓库层面 MIT，未声明数据许可"
    },
    "evidence": [
      {
        "location": "repo-license",
        "location_detail": {
          "en": "GitHub repository license: MIT; data or code users must cite the paper",
          "zh": "GitHub 仓库许可证：MIT；使用数据或代码须引用论文"
        },
        "excerpt": "MIT License\nCopyright (c) 2022 Di Jin",
        "spdx": "MIT",
        "url": "https://github.com/jind11/MedQA",
        "verified_on": "2026-11-12",
        "snapshot_id": "s02",
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "unstated",
  "hosting": "pending",
  "hosting_reason": {
    "zh": "许可证未声明许可：仅仓库层面 MIT，未声明数据许可；确认前只链接原出处。",
    "en": "License unstated: Repository-level MIT only; no data license stated; link only until resolved."
  },
  "signoff": null,
  "repo_license": {
    "spdx": "MIT",
    "source": "license-file",
    "verified": true,
    "snapshot_id": "s02",
    "url": "https://github.com/jind11/MedQA"
  },
  "risk_flags": [
    "exam-derived"
  ],
  "provenance": {
    "source_description": {
      "en": "Medical licensing exam questions and textbooks",
      "zh": "医师资格考试题与教材"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "The page does not mention MCMLE; details of the Chinese subset not verified",
      "zh": "页面未出现 MCMLE 字样，中文子集细节未核实"
    },
    {
      "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/jind11/MedQA"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": [
      "arXiv:2009.13081"
    ]
  },
  "verification_level": "verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "source_type",
      "value": "textbook-reference",
      "basis": "author-stated",
      "excerpt": "- For textbooks, we have two languages: English and simplified Chinese. For simplified Chinese, we provide two kinds of sentence spliting: one is split by sentences, and the other is split by paragraphs.",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "jsonl",
      "basis": "author-stated",
      "excerpt": "na, and Taiwan District, which are put in folders, respectively. All files for QAs are in jsonl file format, where each line is a data sample as a dict. The \"XX_qbank.jsonl\" files conta",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "retrieval-kb",
      "basis": "author-stated",
      "excerpt": "is step, we need to inject all medical textbooks into the server so that it will act as a knowledge base for IR. In the \"IR/scripts\" folder, the file of \"insert_text_to_elasticsearch.py\" is for",
      "snapshot_id": "s01",
      "scope": {
        "en": "textbooks",
        "zh": "教材部分"
      }
    },
    {
      "facet": "task_format",
      "value": "choice-question",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Four-option questions.",
        "zh": "四选项题"
      }
    },
    {
      "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": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 4 (3 stated by the authors with excerpts, 1 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 4 个（作者声明 3 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": "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": "jind11/MedQA",
    "source": {
      "api_url": "https://api.github.com/repos/jind11/MedQA",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "git clone https://github.com/jind11/MedQA",
        "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": "2022-12-01T18:23:49Z",
      "default_branch": "master"
    },
    "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": "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：MedQA (USMLE 4-option, US subset + English textbook corpus) (https://mdexa.com/zh/datasets/medqa-2/)；医学考试题库 JSON 数据集 (https://mdexa.com/zh/datasets/medical-exam-question-bank-json/)；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": "MedQA (USMLE 4-option, US subset + English textbook corpus)",
        "url": "https://mdexa.com/zh/datasets/medqa-2/",
        "json": "https://mdexa.com/zh/datasets/medqa-2.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"
      },
      {
        "name": "CMB (Chinese Medical Benchmark)",
        "url": "https://mdexa.com/zh/datasets/cmb/",
        "json": "https://mdexa.com/zh/datasets/cmb.json"
      }
    ]
  }
}