{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:23C7IXMTP6GIGK5COEEQ726BS2","short_pith_number":"pith:23C7IXMT","schema_version":"1.0","canonical_sha256":"d6c5f45d937f8c832ba271090febc1968954ea2a128dbb6a9294dc8328214136","source":{"kind":"arxiv","id":"2510.03844","version":1},"attestation_state":"computed","paper":{"title":"On Using Large Language Models to Enhance Clinically-Driven Missing Data Recovery Algorithms in Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.ME"],"primary_cat":"cs.LG","authors_text":"Abbey Collins, Ashish K. Khanna, Brian J. Wells, Joseph Rigdon, Lucy D'Agostino McGowan, Sarah C. Lotspeich","submitted_at":"2025-10-04T15:45:22Z","abstract_excerpt":"Objective: Electronic health records (EHR) data are prone to missingness and errors. Previously, we devised an \"enriched\" chart review protocol where a \"roadmap\" of auxiliary diagnoses (anchors) was used to recover missing values in EHR data (e.g., a diagnosis of impaired glycemic control might imply that a missing hemoglobin A1c value would be considered unhealthy). Still, chart reviews are expensive and time-intensive, which limits the number of patients whose data can be reviewed. Now, we investigate the accuracy and scalability of a roadmap-driven algorithm, based on ICD-10 codes (Internat"},"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":"2510.03844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-04T15:45:22Z","cross_cats_sorted":["stat.AP","stat.ME"],"title_canon_sha256":"54a3028097ebc611b2d6e29e750272ef8fda77587bf08a528952e37a06fc697e","abstract_canon_sha256":"de0eb5cb94a74c6fbeea251286a35b81dbcc134a9b66aaffb7b8383a7c56af1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:25.840077Z","signature_b64":"rsbDU4CmfNUPmDyfSneW38YYkj5/6MdgjiQqEKlia/9y2IKMg+IHS92EagztqAlWQ66fSnCJTan7YxRgcnlkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6c5f45d937f8c832ba271090febc1968954ea2a128dbb6a9294dc8328214136","last_reissued_at":"2026-06-10T00:08:25.839028Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:25.839028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Using Large Language Models to Enhance Clinically-Driven Missing Data Recovery Algorithms in Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.ME"],"primary_cat":"cs.LG","authors_text":"Abbey Collins, Ashish K. Khanna, Brian J. Wells, Joseph Rigdon, Lucy D'Agostino McGowan, Sarah C. Lotspeich","submitted_at":"2025-10-04T15:45:22Z","abstract_excerpt":"Objective: Electronic health records (EHR) data are prone to missingness and errors. Previously, we devised an \"enriched\" chart review protocol where a \"roadmap\" of auxiliary diagnoses (anchors) was used to recover missing values in EHR data (e.g., a diagnosis of impaired glycemic control might imply that a missing hemoglobin A1c value would be considered unhealthy). Still, chart reviews are expensive and time-intensive, which limits the number of patients whose data can be reviewed. Now, we investigate the accuracy and scalability of a roadmap-driven algorithm, based on ICD-10 codes (Internat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03844","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/2510.03844/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":"2510.03844","created_at":"2026-06-10T00:08:25.839179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.03844v1","created_at":"2026-06-10T00:08:25.839179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03844","created_at":"2026-06-10T00:08:25.839179+00:00"},{"alias_kind":"pith_short_12","alias_value":"23C7IXMTP6GI","created_at":"2026-06-10T00:08:25.839179+00:00"},{"alias_kind":"pith_short_16","alias_value":"23C7IXMTP6GIGK5C","created_at":"2026-06-10T00:08:25.839179+00:00"},{"alias_kind":"pith_short_8","alias_value":"23C7IXMT","created_at":"2026-06-10T00:08:25.839179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23C7IXMTP6GIGK5COEEQ726BS2","json":"https://pith.science/pith/23C7IXMTP6GIGK5COEEQ726BS2.json","graph_json":"https://pith.science/api/pith-number/23C7IXMTP6GIGK5COEEQ726BS2/graph.json","events_json":"https://pith.science/api/pith-number/23C7IXMTP6GIGK5COEEQ726BS2/events.json","paper":"https://pith.science/paper/23C7IXMT"},"agent_actions":{"view_html":"https://pith.science/pith/23C7IXMTP6GIGK5COEEQ726BS2","download_json":"https://pith.science/pith/23C7IXMTP6GIGK5COEEQ726BS2.json","view_paper":"https://pith.science/paper/23C7IXMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.03844&json=true","fetch_graph":"https://pith.science/api/pith-number/23C7IXMTP6GIGK5COEEQ726BS2/graph.json","fetch_events":"https://pith.science/api/pith-number/23C7IXMTP6GIGK5COEEQ726BS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23C7IXMTP6GIGK5COEEQ726BS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23C7IXMTP6GIGK5COEEQ726BS2/action/storage_attestation","attest_author":"https://pith.science/pith/23C7IXMTP6GIGK5COEEQ726BS2/action/author_attestation","sign_citation":"https://pith.science/pith/23C7IXMTP6GIGK5COEEQ726BS2/action/citation_signature","submit_replication":"https://pith.science/pith/23C7IXMTP6GIGK5COEEQ726BS2/action/replication_record"}},"created_at":"2026-06-10T00:08:25.839179+00:00","updated_at":"2026-06-10T00:08:25.839179+00:00"}