{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2TCGKBIJI4ZWH7S7N7NEUR4PSM","short_pith_number":"pith:2TCGKBIJ","schema_version":"1.0","canonical_sha256":"d4c4650509473363fe5f6fda4a478f933c3a083ebac9ad89f4de53b289952922","source":{"kind":"arxiv","id":"2501.00644","version":1},"attestation_state":"computed","paper":{"title":"Efficient Standardization of Clinical Notes using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniel B. Hier, Michael D. Carrithers, Tayo Obafemi-Ajayi, Thanh Son Do","submitted_at":"2024-12-31T20:52:40Z","abstract_excerpt":"Clinician notes are a rich source of patient information but often contain inconsistencies due to varied writing styles, colloquialisms, abbreviations, medical jargon, grammatical errors, and non-standard formatting. These inconsistencies hinder the extraction of meaningful data from electronic health records (EHRs), posing challenges for quality improvement, population health, precision medicine, decision support, and research.\n  We present a large language model approach to standardizing a corpus of 1,618 clinical notes. Standardization corrected an average of $4.9 +/- 1.8$ grammatical error"},"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":"2501.00644","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T20:52:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dd611a07d7e776f85508bbc206ec4e80edb07b73f42ec255c1f91ae2bbe513b7","abstract_canon_sha256":"3c322abce9befada305e19f7e5aa5ad18b810078127c682f7e093598222a9614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:08.588215Z","signature_b64":"DD2Xw6nDRFIj1cY12QttE7G44wo0MTUVwZm5Xcc1nO3HOahB/0TtI11aT0Fpoj1NG/oAltHc3UDwh/R43ie0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4c4650509473363fe5f6fda4a478f933c3a083ebac9ad89f4de53b289952922","last_reissued_at":"2026-07-05T09:56:08.587793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:08.587793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Standardization of Clinical Notes using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniel B. Hier, Michael D. Carrithers, Tayo Obafemi-Ajayi, Thanh Son Do","submitted_at":"2024-12-31T20:52:40Z","abstract_excerpt":"Clinician notes are a rich source of patient information but often contain inconsistencies due to varied writing styles, colloquialisms, abbreviations, medical jargon, grammatical errors, and non-standard formatting. These inconsistencies hinder the extraction of meaningful data from electronic health records (EHRs), posing challenges for quality improvement, population health, precision medicine, decision support, and research.\n  We present a large language model approach to standardizing a corpus of 1,618 clinical notes. Standardization corrected an average of $4.9 +/- 1.8$ grammatical error"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00644","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/2501.00644/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":"2501.00644","created_at":"2026-07-05T09:56:08.587852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00644v1","created_at":"2026-07-05T09:56:08.587852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00644","created_at":"2026-07-05T09:56:08.587852+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TCGKBIJI4ZW","created_at":"2026-07-05T09:56:08.587852+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TCGKBIJI4ZWH7S7","created_at":"2026-07-05T09:56:08.587852+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TCGKBIJ","created_at":"2026-07-05T09:56:08.587852+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/2TCGKBIJI4ZWH7S7N7NEUR4PSM","json":"https://pith.science/pith/2TCGKBIJI4ZWH7S7N7NEUR4PSM.json","graph_json":"https://pith.science/api/pith-number/2TCGKBIJI4ZWH7S7N7NEUR4PSM/graph.json","events_json":"https://pith.science/api/pith-number/2TCGKBIJI4ZWH7S7N7NEUR4PSM/events.json","paper":"https://pith.science/paper/2TCGKBIJ"},"agent_actions":{"view_html":"https://pith.science/pith/2TCGKBIJI4ZWH7S7N7NEUR4PSM","download_json":"https://pith.science/pith/2TCGKBIJI4ZWH7S7N7NEUR4PSM.json","view_paper":"https://pith.science/paper/2TCGKBIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00644&json=true","fetch_graph":"https://pith.science/api/pith-number/2TCGKBIJI4ZWH7S7N7NEUR4PSM/graph.json","fetch_events":"https://pith.science/api/pith-number/2TCGKBIJI4ZWH7S7N7NEUR4PSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TCGKBIJI4ZWH7S7N7NEUR4PSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TCGKBIJI4ZWH7S7N7NEUR4PSM/action/storage_attestation","attest_author":"https://pith.science/pith/2TCGKBIJI4ZWH7S7N7NEUR4PSM/action/author_attestation","sign_citation":"https://pith.science/pith/2TCGKBIJI4ZWH7S7N7NEUR4PSM/action/citation_signature","submit_replication":"https://pith.science/pith/2TCGKBIJI4ZWH7S7N7NEUR4PSM/action/replication_record"}},"created_at":"2026-07-05T09:56:08.587852+00:00","updated_at":"2026-07-05T09:56:08.587852+00:00"}