{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "mlec-qa",
  "name": "MLEC-QA",
  "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",
    "traditional-medicine"
  ],
  "domains": [
    "clinical-medicine",
    "public-health",
    "tcm"
  ],
  "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": "136,236道选择题，5个子集（临床、口腔、公共卫生、中医、中西医结合），各有训/验/测",
    "measures": [
      {
        "value": 136236,
        "unit": "questions",
        "qualifier": "exact",
        "scope": "total, 5 subsets"
      }
    ]
  },
  "publisher": "Judenpech（EMNLP 2021 论文作者）",
  "year": {
    "value": 2021,
    "raw": "2021"
  },
  "expert_review": {
    "en": "Questions written by experts (README)",
    "zh": "题目为专家编写（README）"
  },
  "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",
          "zh": "GitHub 仓库许可证：MIT"
        },
        "excerpt": "MIT License\nCopyright (c) 2021 Jing Li",
        "spdx": "MIT",
        "url": "https://github.com/Judenpech/MLEC-QA",
        "verified_on": "2026-11-12",
        "snapshot_id": "s02",
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "README has no separate data license; only asks to cite the paper [Note: No license statement seen in snapshot s01, s02, s03]",
          "zh": "README 无单独数据许可，仅要求引用论文［备注：快照中未见许可声明（快照 s01, s02, s03）］"
        },
        "excerpt": null,
        "spdx": null,
        "url": "https://github.com/Judenpech/MLEC-QA",
        "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：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/Judenpech/MLEC-QA"
  },
  "risk_flags": [
    "exam-derived"
  ],
  "provenance": {
    "source_description": {
      "en": "National Medical Licensing Examination question bank (NMLEC)",
      "zh": "国家医学考试题库（NMLEC）"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "MIT is the repository license; no separate data license",
      "zh": "MIT 为仓库许可证，未单独说明数据许可"
    },
    {
      "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"
    },
    {
      "en": "Some questions contain images or tables",
      "zh": "部分题含图片或表格"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://github.com/Judenpech/MLEC-QA"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "task_format",
      "value": "choice-question",
      "basis": "author-stated",
      "excerpt": "MLEC-QA is a Chinese multi-choice Biomedical Question Answering Dataset. Questions in MLEC-QA are collected from the [Natio",
      "snapshot_id": "s01"
    },
    {
      "facet": "official_split",
      "value": "full-split",
      "basis": "author-stated",
      "excerpt": "- Clinic (临床): `Clinic_{train,dev,test}.json`",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "json",
      "basis": "author-stated",
      "excerpt": "The JSON dataset file format is as follows:",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "We hope the release of the MLEC-QA dataset can serve as a valuable resource for research and evaluation in Open-domain QA, and also make advances for Biomedical Question Answering systems.",
      "snapshot_id": "s01"
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-size",
      "note": {
        "zh": "含临床、口腔、公共卫生、中医、中西医结合五个子集",
        "en": "Five subsets incl. clinical, stomatology, public health, TCM"
      }
    }
  ],
  "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: 5 (4 stated by the authors with excerpts, 1 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 5 个（作者声明 4 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 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": "Judenpech/MLEC-QA",
    "source": {
      "api_url": "https://api.github.com/repos/Judenpech/MLEC-QA",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "git clone https://github.com/Judenpech/MLEC-QA",
        "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": "2021-11-05T03:59:13Z",
      "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: 医学考试题库 JSON 数据集 (https://mdexa.com/datasets/medical-exam-question-bank-json/); CMB (Chinese Medical Benchmark) (https://mdexa.com/datasets/cmb/); MedMCQA (https://mdexa.com/datasets/medmcqa/).",
    "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": "医学考试题库 JSON 数据集",
        "url": "https://mdexa.com/datasets/medical-exam-question-bank-json/",
        "json": "https://mdexa.com/datasets/medical-exam-question-bank-json.json"
      },
      {
        "name": "CMB (Chinese Medical Benchmark)",
        "url": "https://mdexa.com/datasets/cmb/",
        "json": "https://mdexa.com/datasets/cmb.json"
      },
      {
        "name": "MedMCQA",
        "url": "https://mdexa.com/datasets/medmcqa/",
        "json": "https://mdexa.com/datasets/medmcqa.json"
      }
    ]
  }
}