{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "bianque-corpus",
  "name": "BianQueCorpus（扁鹊健康大数据）",
  "summary": {
    "zh": "许可证声明：有限制（LicenseRef-THUDM-ChatGLM-6B-Model-License）；本站处理：只链接原出处。许可证有限制：官方 README 写明本项目仅可用于非商业研究，按\"限制从宽认定\"对语料有效；只链接原出处。",
    "en": "License: restricted (LicenseRef-THUDM-ChatGLM-6B-Model-License); Mdexa hosting: link-only. License is restricted: The official README limits the project to non-commercial research; under \"restrictions are read broadly\" this applies to the corpus; link only."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "qa-dialogue"
  ],
  "content_description": {
    "en": "Health dialogue corpus",
    "zh": "健康对话语料"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "README 称千万级规模；BianQue-1.0 训练混合集超过900万条",
    "measures": [
      {
        "value": 10000000,
        "unit": "items",
        "qualifier": "claimed",
        "scope": "README: ten-million scale"
      },
      {
        "value": 9000000,
        "unit": "items",
        "qualifier": "at-least",
        "scope": "BianQue-1.0 training mix"
      }
    ]
  },
  "publisher": "scutcyr / 华南理工大学",
  "year": {
    "value": 2023,
    "raw": "2023（arXiv 2310.15896）"
  },
  "expert_review": {
    "en": "Not stated",
    "zh": "未说明"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "LicenseRef-THUDM-ChatGLM-6B-Model-License",
    "commercial_use": "no",
    "derivatives": "unverified",
    "redistribution": "unverified",
    "rationale": {
      "en": "The official README limits the project to non-commercial research; under \"restrictions are read broadly\" this applies to the corpus",
      "zh": "官方 README 写明本项目仅可用于非商业研究，按\"限制从宽认定\"对语料有效"
    },
    "evidence": [
      {
        "location": "repo-license",
        "location_detail": {
          "en": "Repository Apache-2.0; corpus license not stated [Note: no LICENSE file or sidebar license captured; the README (snapshot s01) shows only an Apache 2 badge linking to ./LICENSE]",
          "zh": "仓库 Apache-2.0；语料未声明许可［备注：未抓到 LICENSE 文件或侧栏许可；README（快照 s01）仅有指向 ./LICENSE 的 Apache 2 徽章］"
        },
        "excerpt": null,
        "spdx": "Apache-2.0",
        "url": "https://github.com/scutcyr/BianQue",
        "verified_on": "2026-11-12",
        "snapshot_id": null,
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "README says the BianQue-2.0 project is for non-commercial research only",
          "zh": "README 写 BianQue-2.0 项目仅可用于非商业研究"
        },
        "excerpt": "需要遵循其 MODEL_LICENSE ，因此， 本项目仅可用于您的非商业研究目的 。",
        "spdx": null,
        "url": "https://github.com/scutcyr/BianQue",
        "verified_on": "2026-11-12",
        "snapshot_id": "s02",
        "observed": "page",
        "secondhand": false
      }
    ],
    "custom_license": true
  },
  "license_status": "restricted",
  "hosting": "link-only",
  "hosting_reason": {
    "zh": "许可证有限制：官方 README 写明本项目仅可用于非商业研究，按\"限制从宽认定\"对语料有效；只链接原出处。",
    "en": "License is restricted: The official README limits the project to non-commercial research; under \"restrictions are read broadly\" this applies to the corpus; link only."
  },
  "signoff": null,
  "repo_license": {
    "spdx": "Apache-2.0",
    "source": "badge-only",
    "verified": false,
    "snapshot_id": null,
    "url": "https://github.com/scutcyr/BianQue"
  },
  "risk_flags": [
    "derived",
    "scraped",
    "real-patient-text"
  ],
  "provenance": {
    "source_description": {
      "en": "Integrates MedDialog-CN, IMCS-V2, CHIP-MDCFNPC, MedDG, cMedQA2, Chinese-medical-dialogue-data and lab-built data",
      "zh": "整合 MedDialog-CN、IMCS-V2、CHIP-MDCFNPC、MedDG、cMedQA2、Chinese-medical-dialogue-data 及实验室自建数据"
    },
    "upstream": [
      {
        "slug": "meddialog-cn",
        "name": "MedDialog-CN",
        "relation": "includes"
      },
      {
        "slug": null,
        "name": "IMCS-V2",
        "relation": "includes"
      },
      {
        "slug": null,
        "name": "CHIP-MDCFNPC",
        "relation": "includes"
      },
      {
        "slug": "meddg",
        "name": "MedDG",
        "relation": "includes"
      },
      {
        "slug": "cmedqa2",
        "name": "cMedQA2",
        "relation": "includes"
      },
      {
        "slug": "chinese-medical-dialogue-data",
        "name": "Chinese-medical-dialogue-data",
        "relation": "includes"
      }
    ]
  },
  "known_issues": [
    {
      "en": "Upstream datasets have differing terms",
      "zh": "上游多个数据集条款各异"
    },
    {
      "en": "Whether the non-commercial statement covers the corpus is not stated",
      "zh": "非商业声明是否覆盖语料未说明"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://github.com/scutcyr/BianQue"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": [
      "arXiv:2310.15896"
    ]
  },
  "verification_level": "verified-no-license-statement",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "intended_use",
      "value": "fine-tuning",
      "basis": "author-stated",
      "excerpt": "* 经过千万规模中文健康对话数据指令微调的[生活空间健康大模型扁鹊（BianQue）](https://github.com/scutcyr/BianQue)",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "multi-turn-dialogue",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Card describes multi-turn health dialogues.",
        "zh": "卡片内容描述为多轮健康对话"
      }
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "zh": "综合健康对话语料，未限定专科",
        "en": "综合健康对话语料; 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 unstated to restricted: restrictions are read broadly; a project-wide restriction in the official release description applies to the data.",
        "zh": "许可状态由未声明改为受限：限制从宽认定，官方说明里针对整个项目的限制对数据有效。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 3 (1 stated by the authors with excerpts, 2 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 3 个（作者声明 1 个，附逐字摘录；据内容推断 2 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)。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Recorded as a custom license: the README requires following the ChatGLM-6B model license; its text was not captured, so derivatives and redistribution are unverified. Status and hosting unchanged.",
        "zh": "记为自定义许可：README 要求遵循 ChatGLM-6B 的模型许可证，许可正文未取证，改编与再分发记为不明；状态与处理方式不变。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "github",
    "repo_id": "scutcyr/BianQue",
    "source": {
      "api_url": "https://api.github.com/repos/scutcyr/BianQue",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "git clone https://github.com/scutcyr/BianQue",
        "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": "2023-10-25T17:43:45Z",
      "default_branch": "main"
    },
    "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": "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: CMtMedQA (https://mdexa.com/datasets/cmtmedqa/); DISC-Med-SFT (https://mdexa.com/datasets/disc-med-sft/); Huatuo-Llama-Med-Chinese 知识库问答与文献数据 (https://mdexa.com/datasets/huatuo-llama-med-chinese-data/).",
    "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": "CMtMedQA",
        "url": "https://mdexa.com/datasets/cmtmedqa/",
        "json": "https://mdexa.com/datasets/cmtmedqa.json"
      },
      {
        "name": "DISC-Med-SFT",
        "url": "https://mdexa.com/datasets/disc-med-sft/",
        "json": "https://mdexa.com/datasets/disc-med-sft.json"
      },
      {
        "name": "Huatuo-Llama-Med-Chinese 知识库问答与文献数据",
        "url": "https://mdexa.com/datasets/huatuo-llama-med-chinese-data/",
        "json": "https://mdexa.com/datasets/huatuo-llama-med-chinese-data.json"
      }
    ]
  }
}