{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MKE4ZF3AHEELY7STLZ4L6G4KND","short_pith_number":"pith:MKE4ZF3A","schema_version":"1.0","canonical_sha256":"6289cc97603908bc7e535e78bf1b8a68ea4dccd94d6ffae450361b597693988b","source":{"kind":"arxiv","id":"2502.06252","version":2},"attestation_state":"computed","paper":{"title":"CliniQ: A Multi-faceted Benchmark for Electronic Health Record Retrieval with Semantic Match Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Haichao Chen, Hongyi Yuan, Huaiyuan Ying, Jingjing Liu, Sheng Yu, Songchi Zhou, Yue Zhong, Zhengyun Zhao","submitted_at":"2025-02-10T08:33:47Z","abstract_excerpt":"Electronic Health Record (EHR) retrieval plays a pivotal role in various clinical tasks, but its development has been severely impeded by the lack of publicly available benchmarks. In this paper, we introduce a novel public EHR retrieval benchmark, CliniQ, to address this gap. We consider two retrieval settings: Single-Patient Retrieval and Multi-Patient Retrieval, reflecting various real-world scenarios. Single-Patient Retrieval focuses on finding relevant parts within a patient note, while Multi-Patient Retrieval involves retrieving EHRs from multiple patients. We build our benchmark upon 1,"},"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":"2502.06252","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-10T08:33:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"260aa7381afe61326317c907f47071a5d9b1dee28ea458638d4ebae4c11baea6","abstract_canon_sha256":"e56ee3dbb778afb81eded96d46957b07b69963a9f5ecd2f1527a7949d765df92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:00.031546Z","signature_b64":"GuIj26lcTJlVLsh5WtrP5ZshLaj6chvdQd5mPuXAEXiDqynVUi5s8m5UMSiC1KOBbzRtbx2z0A7aCCRyvHjRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6289cc97603908bc7e535e78bf1b8a68ea4dccd94d6ffae450361b597693988b","last_reissued_at":"2026-07-05T10:46:00.031059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:00.031059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CliniQ: A Multi-faceted Benchmark for Electronic Health Record Retrieval with Semantic Match Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Haichao Chen, Hongyi Yuan, Huaiyuan Ying, Jingjing Liu, Sheng Yu, Songchi Zhou, Yue Zhong, Zhengyun Zhao","submitted_at":"2025-02-10T08:33:47Z","abstract_excerpt":"Electronic Health Record (EHR) retrieval plays a pivotal role in various clinical tasks, but its development has been severely impeded by the lack of publicly available benchmarks. In this paper, we introduce a novel public EHR retrieval benchmark, CliniQ, to address this gap. We consider two retrieval settings: Single-Patient Retrieval and Multi-Patient Retrieval, reflecting various real-world scenarios. Single-Patient Retrieval focuses on finding relevant parts within a patient note, while Multi-Patient Retrieval involves retrieving EHRs from multiple patients. We build our benchmark upon 1,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06252","kind":"arxiv","version":2},"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/2502.06252/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":"2502.06252","created_at":"2026-07-05T10:46:00.031115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06252v2","created_at":"2026-07-05T10:46:00.031115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06252","created_at":"2026-07-05T10:46:00.031115+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKE4ZF3AHEEL","created_at":"2026-07-05T10:46:00.031115+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKE4ZF3AHEELY7ST","created_at":"2026-07-05T10:46:00.031115+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKE4ZF3A","created_at":"2026-07-05T10:46:00.031115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":167,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKE4ZF3AHEELY7STLZ4L6G4KND","json":"https://pith.science/pith/MKE4ZF3AHEELY7STLZ4L6G4KND.json","graph_json":"https://pith.science/api/pith-number/MKE4ZF3AHEELY7STLZ4L6G4KND/graph.json","events_json":"https://pith.science/api/pith-number/MKE4ZF3AHEELY7STLZ4L6G4KND/events.json","paper":"https://pith.science/paper/MKE4ZF3A"},"agent_actions":{"view_html":"https://pith.science/pith/MKE4ZF3AHEELY7STLZ4L6G4KND","download_json":"https://pith.science/pith/MKE4ZF3AHEELY7STLZ4L6G4KND.json","view_paper":"https://pith.science/paper/MKE4ZF3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06252&json=true","fetch_graph":"https://pith.science/api/pith-number/MKE4ZF3AHEELY7STLZ4L6G4KND/graph.json","fetch_events":"https://pith.science/api/pith-number/MKE4ZF3AHEELY7STLZ4L6G4KND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKE4ZF3AHEELY7STLZ4L6G4KND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKE4ZF3AHEELY7STLZ4L6G4KND/action/storage_attestation","attest_author":"https://pith.science/pith/MKE4ZF3AHEELY7STLZ4L6G4KND/action/author_attestation","sign_citation":"https://pith.science/pith/MKE4ZF3AHEELY7STLZ4L6G4KND/action/citation_signature","submit_replication":"https://pith.science/pith/MKE4ZF3AHEELY7STLZ4L6G4KND/action/replication_record"}},"created_at":"2026-07-05T10:46:00.031115+00:00","updated_at":"2026-07-05T10:46:00.031115+00:00"}