{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "pmc-patients-recds",
  "name": "PMC-Patients-ReCDS",
  "summary": {
    "en": "License: restricted (CC-BY-NC-SA-4.0); Mdexa hosting: link-only. restrictions are read broadly: CC-BY-NC-SA-4.0 Risk flag(s): derived, real-patient-text.",
    "zh": "许可证声明：受限（CC-BY-NC-SA-4.0）；本站处理：只链接原出处。限制从宽认定。来源风险标记：derived、real-patient-text。"
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine",
    "biomedical-literature"
  ],
  "content_types": [
    "annotated-corpus",
    "clinical-cases",
    "literature"
  ],
  "content_description": {
    "en": "PMC-Patients benchmarks Retrieval-based Clinical Decision Support (ReCDS) using patient summaries from PMC case reports, with Patient-to-Article (PAR) and Patient-to-Patient (PPR) retrieval tasks.",
    "zh": "PMC-Patients 基于 PMC 病例报告中的患者摘要，用于评测基于检索的临床决策支持（ReCDS），包含患者检索文章（PAR）和患者检索患者（PPR）两项任务。"
  },
  "languages": [
    "en"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "167k patient summaries; 3.1M patient-article relevance annotations; 293k patient-patient similarity annotations",
    "measures": []
  },
  "publisher": "zhengyun21",
  "year": {
    "value": 2023,
    "raw": "2023"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "CC-BY-NC-SA-4.0",
    "commercial_use": "no",
    "derivatives": "unstated",
    "redistribution": "unstated",
    "rationale": {
      "en": "restrictions are read broadly: CC-BY-NC-SA-4.0",
      "zh": "限制从宽认定"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Statement found in snapshot s04 (readme)",
          "zh": "在快照 s04（readme）中找到的声明"
        },
        "excerpt": "license: cc-by-nc-sa-4.0",
        "spdx": "CC-BY-NC-SA-4.0",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS",
        "verified_on": "2026-11-12",
        "snapshot_id": "s04",
        "observed": "page",
        "captured_by": "pipeline"
      }
    ],
    "license_conditions": [
      "attribution",
      "share-alike"
    ]
  },
  "license_status": "restricted",
  "hosting": "link-only",
  "hosting_reason": {
    "en": "License restricted: restrictions are read broadly: CC-BY-NC-SA-4.0. Risk flag(s): derived, real-patient-text. Link only.",
    "zh": "许可证受限：限制从宽认定。来源风险标记：derived、real-patient-text。只链接原出处。"
  },
  "signoff": null,
  "risk_flags": [
    "derived",
    "real-patient-text"
  ],
  "provenance": {
    "source_description": null,
    "upstream": [
      {
        "slug": null,
        "name": "PMC-Patients",
        "relation": "derived-from"
      }
    ]
  },
  "known_issues": [
    {
      "en": "The full PAR corpus is too large to upload to Hugging Face; only PMIDs of the included articles are provided.",
      "zh": "完整的 PAR 语料过大，无法上传至 Hugging Face，仅提供所收录文章的 PMID。"
    },
    {
      "en": "Qrels may differ from relevant_articles and similar_patients in PMC-Patients.json because of the dataset split.",
      "zh": "由于数据集划分，qrels 可能与 PMC-Patients.json 中的 relevant_articles 和 similar_patients 不一致。"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": [
      "arXiv:2202.13876"
    ]
  },
  "verification_level": "verified",
  "last_verified": "2026-11-14",
  "tags": [
    {
      "facet": "task_format",
      "value": "text-matching",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "Patient-to-Article Retrieval (PAR) and Patient-to-Patient Retrieval (PPR)",
      "snapshot_id": "s04"
    },
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "we define two tasks to benchmark Retrieval-based Clinical Decision Support (ReCDS) systems",
      "snapshot_id": "s04"
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "167k patient summaries extracted from case reports in PubMed Central (PMC)",
      "snapshot_id": "s04"
    },
    {
      "facet": "source_type",
      "value": "literature",
      "basis": "author-stated",
      "excerpt": "patient summaries extracted from case reports in PubMed Central (PMC)",
      "snapshot_id": "s04"
    },
    {
      "facet": "data_format",
      "value": "jsonl",
      "basis": "author-stated",
      "excerpt": "queries are stored a `jsonl` file that contains a list of dictionaries, each with two fields",
      "snapshot_id": "s04"
    },
    {
      "facet": "data_format",
      "value": "tsv",
      "basis": "author-stated",
      "excerpt": "Qrels are TREC-style retrieval annotation files in `tsv` format.",
      "snapshot_id": "s04"
    },
    {
      "facet": "official_split",
      "value": "full-split",
      "basis": "author-stated",
      "excerpt": "For each split (train, dev, and test), queries are stored a `jsonl` file",
      "snapshot_id": "s04"
    },
    {
      "facet": "expert_involvement",
      "value": "none",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "excerpt": "293k patient-patient similarity annotations defined by PubMed citation graph",
      "snapshot_id": "s04"
    },
    {
      "facet": "benchmark_status",
      "value": "public-leaderboard",
      "basis": "author-stated",
      "excerpt": "**Leaderboard:** https://pmc-patients.github.io/",
      "snapshot_id": "s04"
    }
  ],
  "changelog": [
    {
      "date": "2026-11-14",
      "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": "2026-11-14",
      "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": "zhengyun21/PMC-Patients-ReCDS",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/zhengyun21/PMC-Patients-ReCDS",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/.gitattributes",
        "size_bytes": 2842,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "PAR/PAR_PMIDs.json",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/PAR/PAR_PMIDs.json",
        "size_bytes": 22352129,
        "checksum": {
          "algorithm": "sha256",
          "value": "72249aa91cd6f548f9ff8af9a0f77ed2f41c6e2b60aa93b3b9b196fec88360af"
        },
        "format": "json"
      },
      {
        "name": "PAR/qrels_dev.tsv",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/PAR/qrels_dev.tsv",
        "size_bytes": 2239111,
        "checksum": null,
        "format": "tsv"
      },
      {
        "name": "PAR/qrels_test.tsv",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/PAR/qrels_test.tsv",
        "size_bytes": 2376708,
        "checksum": null,
        "format": "tsv"
      },
      {
        "name": "PAR/qrels_train.tsv",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/PAR/qrels_train.tsv",
        "size_bytes": 60243572,
        "checksum": {
          "algorithm": "sha256",
          "value": "025107882bf24b6137dae2d09ca30db2db1adbcdba4d6ed521af057fb8cf803c"
        },
        "format": "tsv"
      },
      {
        "name": "PPR/corpus.jsonl",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/PPR/corpus.jsonl",
        "size_bytes": 436949038,
        "checksum": {
          "algorithm": "sha256",
          "value": "33c2f31a02816f20de1cadae2dba4ab97518398519aeb1e46ebcb6dca5038058"
        },
        "format": "jsonl"
      },
      {
        "name": "PPR/qrels_dev.tsv",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/PPR/qrels_dev.tsv",
        "size_bytes": 140030,
        "checksum": null,
        "format": "tsv"
      },
      {
        "name": "PPR/qrels_test.tsv",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/PPR/qrels_test.tsv",
        "size_bytes": 164523,
        "checksum": null,
        "format": "tsv"
      },
      {
        "name": "PPR/qrels_train.tsv",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/PPR/qrels_train.tsv",
        "size_bytes": 5666545,
        "checksum": null,
        "format": "tsv"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/README.md",
        "size_bytes": 6207,
        "checksum": null,
        "format": "md"
      },
      {
        "name": "queries/dev_queries.jsonl",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/queries/dev_queries.jsonl",
        "size_bytes": 16527534,
        "checksum": {
          "algorithm": "sha256",
          "value": "e3afe1b5f6832a4c691267453153aaec6af5fd7cdbef567be484a7a1fb48d48b"
        },
        "format": "jsonl"
      },
      {
        "name": "queries/test_queries.jsonl",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/queries/test_queries.jsonl",
        "size_bytes": 16743250,
        "checksum": {
          "algorithm": "sha256",
          "value": "0501920965ef79f53c6efb30d1f8f7b7ba6ff3564da1913db5a515d365cef8b8"
        },
        "format": "jsonl"
      },
      {
        "name": "queries/train_queries.jsonl",
        "url": "https://huggingface.co/datasets/zhengyun21/PMC-Patients-ReCDS/resolve/a27717bb27679cf0860305997685547ca01b3dd1/queries/train_queries.jsonl",
        "size_bytes": 434932075,
        "checksum": {
          "algorithm": "sha256",
          "value": "63647693d797e5be90f6644003483d2a01543f55c02e5474be4ece12fd405b32"
        },
        "format": "jsonl"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download zhengyun21/PMC-Patients-ReCDS --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": "a27717bb27679cf0860305997685547ca01b3dd1",
      "last_modified": "2023-11-07T16:21:59.000Z"
    },
    "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": []
  },
  "_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: PubMedQA (https://mdexa.com/datasets/pubmedqa/); PubMedCausal (https://mdexa.com/datasets/pubmedcausal/); PromptCBLUE (https://mdexa.com/datasets/promptcblue/).",
    "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": "PubMedQA",
        "url": "https://mdexa.com/datasets/pubmedqa/",
        "json": "https://mdexa.com/datasets/pubmedqa.json"
      },
      {
        "name": "PubMedCausal",
        "url": "https://mdexa.com/datasets/pubmedcausal/",
        "json": "https://mdexa.com/datasets/pubmedcausal.json"
      },
      {
        "name": "PromptCBLUE",
        "url": "https://mdexa.com/datasets/promptcblue/",
        "json": "https://mdexa.com/datasets/promptcblue.json"
      }
    ]
  }
}