{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "medqa-usmle-4-options-hf",
  "name": "GBaker/MedQA-USMLE-4-options-hf",
  "summary": {
    "en": "License: permissive, share-alike (CC-BY-SA-4.0); Mdexa hosting: link-only. first-hand data-scope statement(s) allow commercial use and redistribution Risk flag(s): exam-derived.",
    "zh": "许可证声明：宽松，须相同方式共享（CC-BY-SA-4.0）；本站处理：只链接原出处。针对数据的声明允许商用和再分发。来源风险标记：exam-derived。"
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "benchmark-exam",
    "qa-dialogue"
  ],
  "content_description": {
    "en": "Original dataset introduced by Jin et al.: a large-scale open domain question answering dataset from medical exams.",
    "zh": "由Jin等人提出的数据集，源自医学考试的大型开放域问答数据集。"
  },
  "languages": [
    "en"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": null,
    "measures": []
  },
  "publisher": "GBaker",
  "year": {
    "value": 2020,
    "raw": "2020"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "CC-BY-SA-4.0",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "first-hand data-scope statement(s) allow commercial use and redistribution",
      "zh": "针对数据的声明允许商用和再分发"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "license: cc-by-sa-4.0",
        "spdx": "CC-BY-SA-4.0",
        "url": "https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options-hf",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      }
    ],
    "license_conditions": [
      "attribution",
      "share-alike"
    ],
    "notes": {
      "en": "risk flag(s) exam-derived: never eligible or hosted",
      "zh": "risk flag(s) exam-derived: never eligible or hosted"
    }
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "en": "License permissive, share-alike: first-hand data-scope statement(s) allow commercial use and redistribution. Risk flag(s): exam-derived. Link only.",
    "zh": "许可证宽松，须相同方式共享：针对数据的声明允许商用和再分发。来源风险标记：exam-derived。只链接原出处。"
  },
  "signoff": null,
  "risk_flags": [
    "exam-derived"
  ],
  "provenance": {
    "source_description": null,
    "upstream": []
  },
  "known_issues": [],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options-hf"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": [
      "arXiv:2009.13081"
    ]
  },
  "verification_level": "verified",
  "last_verified": "2026-11-14",
  "tags": [
    {
      "facet": "task_format",
      "value": "open-qa",
      "basis": "author-stated",
      "excerpt": "A Large-scale Open Domain Question Answering Dataset from Medical Exams",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "choice-question",
      "basis": "inferred",
      "inferred_from": "snapshot-structure",
      "excerpt": "\"id\": \"GBaker/MedQA-USMLE-4-options-hf\",",
      "snapshot_id": "s03"
    }
  ],
  "changelog": [
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added via the automated pipeline and passed all checks (gates, verbatim quotes, rule engine, two independent extractions).",
        "zh": "经自动流水线收录并通过全部校验（门禁、逐字引用、判定引擎、两轮独立抽取）。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "GBaker/MedQA-USMLE-4-options-hf",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/GBaker/MedQA-USMLE-4-options-hf",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options-hf/resolve/17af9355ef89fba60de966eabaeba797c695f86e/.gitattributes",
        "size_bytes": 2265,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options-hf/resolve/17af9355ef89fba60de966eabaeba797c695f86e/README.md",
        "size_bytes": 640,
        "checksum": null,
        "format": "md"
      },
      {
        "name": "dev.json",
        "url": "https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options-hf/resolve/17af9355ef89fba60de966eabaeba797c695f86e/dev.json",
        "size_bytes": 1219664,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "test.json",
        "url": "https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options-hf/resolve/17af9355ef89fba60de966eabaeba797c695f86e/test.json",
        "size_bytes": 1248464,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "train.json",
        "url": "https://huggingface.co/datasets/GBaker/MedQA-USMLE-4-options-hf/resolve/17af9355ef89fba60de966eabaeba797c695f86e/train.json",
        "size_bytes": 9770763,
        "checksum": null,
        "format": "json"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download GBaker/MedQA-USMLE-4-options-hf --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": "17af9355ef89fba60de966eabaeba797c695f86e",
      "last_modified": "2023-01-30T22:57:33.000Z"
    },
    "license_note": {
      "license_status": "permissive",
      "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-options (https://mdexa.com/zh/datasets/medqa-usmle-4-options/)；MedMCQA (https://mdexa.com/zh/datasets/medmcqa/)；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-options",
        "url": "https://mdexa.com/zh/datasets/medqa-usmle-4-options/",
        "json": "https://mdexa.com/zh/datasets/medqa-usmle-4-options.json"
      },
      {
        "name": "MedMCQA",
        "url": "https://mdexa.com/zh/datasets/medmcqa/",
        "json": "https://mdexa.com/zh/datasets/medmcqa.json"
      },
      {
        "name": "CMB (Chinese Medical Benchmark)",
        "url": "https://mdexa.com/zh/datasets/cmb/",
        "json": "https://mdexa.com/zh/datasets/cmb.json"
      }
    ]
  }
}