{ "schema_version": "2.0", "record_type": "dataset", "tier": "verified", "slug": "cmedqa2", "name": "cMedQA2", "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 限定非商业研究；只链接原出处。", "en": "License: restricted (NOASSERTION); Mdexa hosting: link-only. License is restricted: README limits use to non-commercial research; link only." }, "systems": [ "modern-medicine" ], "domains": [ "clinical-medicine" ], "content_types": [ "qa-dialogue" ], "content_description": { "en": "Community QA corpus", "zh": "社区问答语料" }, "languages": [ "zh" ], "modalities": [ "text" ], "size": { "raw": "108,000问题、203,569回答（训练100,000问/188,490答）", "measures": [ { "value": 108000, "unit": "questions", "qualifier": "exact", "scope": "total" }, { "value": 203569, "unit": "answers", "qualifier": "exact", "scope": "total" }, { "value": 100000, "unit": "questions", "qualifier": "exact", "scope": "train" }, { "value": 188490, "unit": "answers", "qualifier": "exact", "scope": "train" } ] }, "publisher": "zhangsheng93（IEEE Access 论文，S. Zhang 等）", "year": { "value": 2018, "raw": "2018" }, "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 limits use to non-commercial research", "zh": "README 限定非商业研究" }, "evidence": [ { "location": "repo-license", "location_detail": { "en": "GitHub repository license: GPL-3.0", "zh": "GitHub 仓库许可证：GPL-3.0" }, "excerpt": "GNU GENERAL PUBLIC LICENSE\nVersion 3, 29 June 2007", "spdx": "GPL-3.0", "url": "https://github.com/zhangsheng93/cMedQA2", "verified_on": "2026-11-12", "snapshot_id": "s02", "observed": "page", "secondhand": false }, { "location": "readme", "location_detail": { "en": "README non-commercial research statement for version 2.0", "zh": "README 版本 2.0 非商业研究声明" }, "excerpt": "available for non-commercial research", "spdx": null, "url": "https://github.com/zhangsheng93/cMedQA2", "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 限定非商业研究；只链接原出处。", "en": "License is restricted: README limits use to non-commercial research; link only." }, "signoff": null, "repo_license": { "spdx": "GPL-3.0", "source": "license-file", "verified": true, "snapshot_id": "s02", "url": "https://github.com/zhangsheng93/cMedQA2" }, "risk_flags": [], "provenance": { "source_description": { "en": "Chinese medical community QA (platform not named on the page)", "zh": "中文医学社区问答（页面未写平台名）" }, "upstream": [] }, "known_issues": [ { "en": "GPL-3.0 coexists with a non-commercial research statement", "zh": "GPL-3.0 与非商业研究声明并存" }, { "en": "Users anonymized", "zh": "用户匿名化" }, { "en": "Source platform not stated", "zh": "平台来源未说明" } ], "preflight": { "status": "not-run" }, "access": { "mdexa_download": null, "external_urls": [ "https://github.com/zhangsheng93/cMedQA2" ], "notes": null }, "citation": { "text": null, "bibtex": null, "references": [] }, "verification_level": "verified", "last_verified": "2026-11-12", "tags": [ { "facet": "official_split", "value": "full-split", "basis": "author-stated", "excerpt": "* **train_candidates.txt** **dev_candidates.txt** **test_candidates.txt** The split of training set, development set and test set respectively.", "snapshot_id": "s01" }, { "facet": "data_format", "value": "csv", "basis": "author-stated", "excerpt": "* **questions.csv** All Questions and their content.", "snapshot_id": "s01" }, { "facet": "task_format", "value": "text-matching", "basis": "inferred", "inferred_from": "card-content-description", "note": { "en": "Answer selection.", "zh": "问答匹配（答案选择）" } }, { "facet": "task_format", "value": "open-qa", "basis": "inferred", "inferred_from": "card-content-description", "note": { "en": "Questions with doctor answers.", "zh": "问题与医生回答" } }, { "facet": "specialty", "value": "multi-specialty", "basis": "inferred", "inferred_from": "card-content-description", "note": { "zh": "综合社区医疗问答，未限定专科", "en": "综合社区医疗问答; 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: 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": "github", "repo_id": "zhangsheng93/cMedQA2", "source": { "api_url": "https://api.github.com/repos/zhangsheng93/cMedQA2", "fetched_on": "2026-11-14" }, "access_state": "open", "files": [], "files_truncated": false, "commands": [ { "command": "git clone https://github.com/zhangsheng93/cMedQA2", "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": "2019-01-09T01:09:09Z", "default_branch": "master" }, "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：Chinese-medical-dialogue-data（Toyhom） (https://mdexa.com/zh/datasets/chinese-medical-dialogue-data/)；HuatuoGPT2-SFT-GPT4-140K (https://mdexa.com/zh/datasets/huatuogpt2-sft-gpt4-140k/)；ChatMed_Consult_Dataset (https://mdexa.com/zh/datasets/chatmed-consult-dataset/)。", "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": "Chinese-medical-dialogue-data（Toyhom）", "url": "https://mdexa.com/zh/datasets/chinese-medical-dialogue-data/", "json": "https://mdexa.com/zh/datasets/chinese-medical-dialogue-data.json" }, { "name": "HuatuoGPT2-SFT-GPT4-140K", "url": "https://mdexa.com/zh/datasets/huatuogpt2-sft-gpt4-140k/", "json": "https://mdexa.com/zh/datasets/huatuogpt2-sft-gpt4-140k.json" }, { "name": "ChatMed_Consult_Dataset", "url": "https://mdexa.com/zh/datasets/chatmed-consult-dataset/", "json": "https://mdexa.com/zh/datasets/chatmed-consult-dataset.json" } ] } }