{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y3EICF25ZD7JALOXBEE3VJRSL7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b286b9ad097aeb79d2b507317d0e93830bc31f176dcc5f28aed46678d7431101","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T21:39:20Z","title_canon_sha256":"5525eb814d934f09701291727daf6518ce64b7d134ff9e172c7c5bcff3dc0d5f"},"schema_version":"1.0","source":{"id":"2407.00242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00242","created_at":"2026-07-05T08:38:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00242v1","created_at":"2026-07-05T08:38:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00242","created_at":"2026-07-05T08:38:16Z"},{"alias_kind":"pith_short_12","alias_value":"Y3EICF25ZD7J","created_at":"2026-07-05T08:38:16Z"},{"alias_kind":"pith_short_16","alias_value":"Y3EICF25ZD7JALOX","created_at":"2026-07-05T08:38:16Z"},{"alias_kind":"pith_short_8","alias_value":"Y3EICF25","created_at":"2026-07-05T08:38:16Z"}],"graph_snapshots":[{"event_id":"sha256:c4a97ab443884d8d79a9666f2575d833a5b681025163d288a02a28460c36a000","target":"graph","created_at":"2026-07-05T08:38:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.00242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Electronic health records (EHRs) contain vast amounts of complex data, but harmonizing and processing this information remains a challenging and costly task requiring significant clinical expertise. While large language models (LLMs) have shown promise in various healthcare applications, their potential for abstracting medical concepts from EHRs remains largely unexplored. We introduce EHRmonize, a framework leveraging LLMs to abstract medical concepts from EHR data. Our study uses medication data from two real-world EHR databases to evaluate five LLMs on two free-text extraction and six binar","authors_text":"A. Ian Wong, Jack Gallifant, Jian Pei, Jo\\~ao Matos","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T21:39:20Z","title":"EHRmonize: A Framework for Medical Concept Abstraction from Electronic Health Records using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00242","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ac0281585b493e64c949d10bd919a31cb3ca1a637ff157ca196f2fc887c849dc","target":"record","created_at":"2026-07-05T08:38:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b286b9ad097aeb79d2b507317d0e93830bc31f176dcc5f28aed46678d7431101","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T21:39:20Z","title_canon_sha256":"5525eb814d934f09701291727daf6518ce64b7d134ff9e172c7c5bcff3dc0d5f"},"schema_version":"1.0","source":{"id":"2407.00242","kind":"arxiv","version":1}},"canonical_sha256":"c6c881175dc8fe902dd70909baa6325fd759dfea19bda96444e3b234103585fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6c881175dc8fe902dd70909baa6325fd759dfea19bda96444e3b234103585fa","first_computed_at":"2026-07-05T08:38:16.468667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:16.468667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NXdTSsB1ITooqn/UkwGkEuuqxYvbXc4+Ln1gUG3aOhR6QLcr8v0T8sp+hW0VtPJwXj6QCfJyPD4d0v9mJgX6BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:16.469110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac0281585b493e64c949d10bd919a31cb3ca1a637ff157ca196f2fc887c849dc","sha256:c4a97ab443884d8d79a9666f2575d833a5b681025163d288a02a28460c36a000"],"state_sha256":"79f34d88a1492c6f901c104019024f7b893ed303c5cbbb15b8bfc6870744ee7a"}