{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FQAYJUK2SS3CAWWSR7RC3NGXWH","short_pith_number":"pith:FQAYJUK2","schema_version":"1.0","canonical_sha256":"2c0184d15a94b6205ad28fe22db4d7b1f2fa583a7b190495be037a9a5fbf3b5f","source":{"kind":"arxiv","id":"2501.18435","version":1},"attestation_state":"computed","paper":{"title":"GENIE: Generative Note Information Extraction model for structuring EHR data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongyi Yuan, Huaiyuan Ying, Isaac Kohane, Jinsen Lu, Sheng Yu, Tianxi Cai, Yang Zhao, Zhengyun Zhao, Zitian Qu","submitted_at":"2025-01-30T15:42:24Z","abstract_excerpt":"Electronic Health Records (EHRs) hold immense potential for advancing healthcare, offering rich, longitudinal data that combines structured information with valuable insights from unstructured clinical notes. However, the unstructured nature of clinical text poses significant challenges for secondary applications. Traditional methods for structuring EHR free-text data, such as rule-based systems and multi-stage pipelines, are often limited by their time-consuming configurations and inability to adapt across clinical notes from diverse healthcare settings. Few systems provide a comprehensive at"},"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":"2501.18435","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T15:42:24Z","cross_cats_sorted":[],"title_canon_sha256":"a4ee0bc8178f0ef5d18e08638fa7790286591004b94e6bfb1e37e2557249a7c1","abstract_canon_sha256":"16cfbb845854ef3d55d2393e94d1d9638e2b5a8af771ed1e68057d09be30e95b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:34.106077Z","signature_b64":"RHvxLTaWBeucCl8/u2ZwheGn3rJ+HTKxyLzlGiDkd6k1qxJ/tOUuZmuOeTF1T070+wNF1xB8bJYGqpk67k02Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c0184d15a94b6205ad28fe22db4d7b1f2fa583a7b190495be037a9a5fbf3b5f","last_reissued_at":"2026-07-05T10:07:34.105650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:34.105650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GENIE: Generative Note Information Extraction model for structuring EHR data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongyi Yuan, Huaiyuan Ying, Isaac Kohane, Jinsen Lu, Sheng Yu, Tianxi Cai, Yang Zhao, Zhengyun Zhao, Zitian Qu","submitted_at":"2025-01-30T15:42:24Z","abstract_excerpt":"Electronic Health Records (EHRs) hold immense potential for advancing healthcare, offering rich, longitudinal data that combines structured information with valuable insights from unstructured clinical notes. However, the unstructured nature of clinical text poses significant challenges for secondary applications. Traditional methods for structuring EHR free-text data, such as rule-based systems and multi-stage pipelines, are often limited by their time-consuming configurations and inability to adapt across clinical notes from diverse healthcare settings. Few systems provide a comprehensive at"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18435","kind":"arxiv","version":1},"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/2501.18435/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":"2501.18435","created_at":"2026-07-05T10:07:34.105714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18435v1","created_at":"2026-07-05T10:07:34.105714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18435","created_at":"2026-07-05T10:07:34.105714+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQAYJUK2SS3C","created_at":"2026-07-05T10:07:34.105714+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQAYJUK2SS3CAWWS","created_at":"2026-07-05T10:07:34.105714+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQAYJUK2","created_at":"2026-07-05T10:07:34.105714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06252","citing_title":"CliniQ: A Multi-faceted Benchmark for Electronic Health Record Retrieval with Semantic Match Assessment","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQAYJUK2SS3CAWWSR7RC3NGXWH","json":"https://pith.science/pith/FQAYJUK2SS3CAWWSR7RC3NGXWH.json","graph_json":"https://pith.science/api/pith-number/FQAYJUK2SS3CAWWSR7RC3NGXWH/graph.json","events_json":"https://pith.science/api/pith-number/FQAYJUK2SS3CAWWSR7RC3NGXWH/events.json","paper":"https://pith.science/paper/FQAYJUK2"},"agent_actions":{"view_html":"https://pith.science/pith/FQAYJUK2SS3CAWWSR7RC3NGXWH","download_json":"https://pith.science/pith/FQAYJUK2SS3CAWWSR7RC3NGXWH.json","view_paper":"https://pith.science/paper/FQAYJUK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18435&json=true","fetch_graph":"https://pith.science/api/pith-number/FQAYJUK2SS3CAWWSR7RC3NGXWH/graph.json","fetch_events":"https://pith.science/api/pith-number/FQAYJUK2SS3CAWWSR7RC3NGXWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQAYJUK2SS3CAWWSR7RC3NGXWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQAYJUK2SS3CAWWSR7RC3NGXWH/action/storage_attestation","attest_author":"https://pith.science/pith/FQAYJUK2SS3CAWWSR7RC3NGXWH/action/author_attestation","sign_citation":"https://pith.science/pith/FQAYJUK2SS3CAWWSR7RC3NGXWH/action/citation_signature","submit_replication":"https://pith.science/pith/FQAYJUK2SS3CAWWSR7RC3NGXWH/action/replication_record"}},"created_at":"2026-07-05T10:07:34.105714+00:00","updated_at":"2026-07-05T10:07:34.105714+00:00"}