{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UZ4Q3Q2GFXKKX7ZWQWJHAZC67H","short_pith_number":"pith:UZ4Q3Q2G","schema_version":"1.0","canonical_sha256":"a6790dc3462dd4abff36859270645ef9fba4d8f49f15e9cc64d0e132dd89d817","source":{"kind":"arxiv","id":"2202.13876","version":4},"attestation_state":"computed","paper":{"title":"PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Fangyuan Chen, Qiao Jin, Sheng Yu, Tuorui Peng, Zhengyun Zhao","submitted_at":"2022-02-28T15:24:33Z","abstract_excerpt":"Objective: Retrieval-based Clinical Decision Support (ReCDS) can aid clinical workflow by providing relevant literature and similar patients for a given patient. However, the development of ReCDS systems has been severely obstructed by the lack of diverse patient collections and publicly available large-scale patient-level annotation datasets. In this paper, we aim to define and benchmark two ReCDS tasks: Patient-to-Article Retrieval (ReCDS-PAR) and Patient-to-Patient Retrieval (ReCDS-PPR) using a novel dataset called PMC-Patients. Methods: We extract patient summaries from PubMed Central arti"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.13876","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-28T15:24:33Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"a35a34bd5780bde0ff2dcb2206b7a882ecd89bc9e5c012134b336345e491936b","abstract_canon_sha256":"7676bff2f00907e1782d1c8b8df70e767a71340fd8e4b33acc929f3df185b244"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:09.952228Z","signature_b64":"iHFhGET482ASHuSYxoEKBnUsNxEc2ebzS45TQGDWyOh5PHGeYO3syyudI7zWs7acBNKqMA2RfOBlhvKq9qz1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6790dc3462dd4abff36859270645ef9fba4d8f49f15e9cc64d0e132dd89d817","last_reissued_at":"2026-07-05T07:26:09.951830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:09.951830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Fangyuan Chen, Qiao Jin, Sheng Yu, Tuorui Peng, Zhengyun Zhao","submitted_at":"2022-02-28T15:24:33Z","abstract_excerpt":"Objective: Retrieval-based Clinical Decision Support (ReCDS) can aid clinical workflow by providing relevant literature and similar patients for a given patient. However, the development of ReCDS systems has been severely obstructed by the lack of diverse patient collections and publicly available large-scale patient-level annotation datasets. In this paper, we aim to define and benchmark two ReCDS tasks: Patient-to-Article Retrieval (ReCDS-PAR) and Patient-to-Patient Retrieval (ReCDS-PPR) using a novel dataset called PMC-Patients. Methods: We extract patient summaries from PubMed Central arti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13876","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.13876/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.13876","created_at":"2026-07-05T07:26:09.951876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13876v4","created_at":"2026-07-05T07:26:09.951876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13876","created_at":"2026-07-05T07:26:09.951876+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZ4Q3Q2GFXKK","created_at":"2026-07-05T07:26:09.951876+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZ4Q3Q2GFXKKX7ZW","created_at":"2026-07-05T07:26:09.951876+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZ4Q3Q2G","created_at":"2026-07-05T07:26:09.951876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03157","citing_title":"ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H","json":"https://pith.science/pith/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H.json","graph_json":"https://pith.science/api/pith-number/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H/graph.json","events_json":"https://pith.science/api/pith-number/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H/events.json","paper":"https://pith.science/paper/UZ4Q3Q2G"},"agent_actions":{"view_html":"https://pith.science/pith/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H","download_json":"https://pith.science/pith/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H.json","view_paper":"https://pith.science/paper/UZ4Q3Q2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13876&json=true","fetch_graph":"https://pith.science/api/pith-number/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H/graph.json","fetch_events":"https://pith.science/api/pith-number/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H/action/storage_attestation","attest_author":"https://pith.science/pith/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H/action/author_attestation","sign_citation":"https://pith.science/pith/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H/action/citation_signature","submit_replication":"https://pith.science/pith/UZ4Q3Q2GFXKKX7ZWQWJHAZC67H/action/replication_record"}},"created_at":"2026-07-05T07:26:09.951876+00:00","updated_at":"2026-07-05T07:26:09.951876+00:00"}