{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WFR4IYYOT5XNVGABHCV5DSY6QT","short_pith_number":"pith:WFR4IYYO","schema_version":"1.0","canonical_sha256":"b163c4630e9f6eda980138abd1cb1e84d83aa7052ee455aee54bcee4edc683ef","source":{"kind":"arxiv","id":"2506.06340","version":1},"attestation_state":"computed","paper":{"title":"Structured Semantics from Unstructured Notes: Language Model Approaches to EHR-Based Decision Support","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Furong Li, Hui Huang, Jian Jiang, Jingyi Lu, Shi Li, Wu Hao Ran, Xi Xi, Yuzhuan Zhang","submitted_at":"2025-06-01T05:07:51Z","abstract_excerpt":"The advent of large language models (LLMs) has opened new avenues for analyzing complex, unstructured data, particularly within the medical domain. Electronic Health Records (EHRs) contain a wealth of information in various formats, including free text clinical notes, structured lab results, and diagnostic codes. This paper explores the application of advanced language models to leverage these diverse data sources for improved clinical decision support. We will discuss how text-based features, often overlooked in traditional high dimensional EHR analysis, can provide semantically rich represen"},"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":"2506.06340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-01T05:07:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98c5e5022b8b55a45ee502cb2b5cb8940a127724dae513c6cc451ebf90287fe7","abstract_canon_sha256":"bfa638e095acacbcd1cdd48e300d73d423c77410b281fde882804427f3a65cfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:48.397171Z","signature_b64":"RiNIX46dlFJy9Qmlzl2Zt63zbIVG8rrq/BQczAx2ymWzIZdXsTwwam/cM8G9EloosCJZCNft4MXhSBzc//ZPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b163c4630e9f6eda980138abd1cb1e84d83aa7052ee455aee54bcee4edc683ef","last_reissued_at":"2026-07-05T11:17:48.396707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:48.396707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Semantics from Unstructured Notes: Language Model Approaches to EHR-Based Decision Support","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Furong Li, Hui Huang, Jian Jiang, Jingyi Lu, Shi Li, Wu Hao Ran, Xi Xi, Yuzhuan Zhang","submitted_at":"2025-06-01T05:07:51Z","abstract_excerpt":"The advent of large language models (LLMs) has opened new avenues for analyzing complex, unstructured data, particularly within the medical domain. Electronic Health Records (EHRs) contain a wealth of information in various formats, including free text clinical notes, structured lab results, and diagnostic codes. This paper explores the application of advanced language models to leverage these diverse data sources for improved clinical decision support. We will discuss how text-based features, often overlooked in traditional high dimensional EHR analysis, can provide semantically rich represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06340","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/2506.06340/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":"2506.06340","created_at":"2026-07-05T11:17:48.396763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06340v1","created_at":"2026-07-05T11:17:48.396763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06340","created_at":"2026-07-05T11:17:48.396763+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFR4IYYOT5XN","created_at":"2026-07-05T11:17:48.396763+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFR4IYYOT5XNVGAB","created_at":"2026-07-05T11:17:48.396763+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFR4IYYO","created_at":"2026-07-05T11:17:48.396763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04175","citing_title":"Uncertainty-Aware Foundation Models for Clinical Data","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08685","citing_title":"Event Fields: Learning Latent Event Structure for Waveform Foundation Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09765","citing_title":"WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WFR4IYYOT5XNVGABHCV5DSY6QT","json":"https://pith.science/pith/WFR4IYYOT5XNVGABHCV5DSY6QT.json","graph_json":"https://pith.science/api/pith-number/WFR4IYYOT5XNVGABHCV5DSY6QT/graph.json","events_json":"https://pith.science/api/pith-number/WFR4IYYOT5XNVGABHCV5DSY6QT/events.json","paper":"https://pith.science/paper/WFR4IYYO"},"agent_actions":{"view_html":"https://pith.science/pith/WFR4IYYOT5XNVGABHCV5DSY6QT","download_json":"https://pith.science/pith/WFR4IYYOT5XNVGABHCV5DSY6QT.json","view_paper":"https://pith.science/paper/WFR4IYYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06340&json=true","fetch_graph":"https://pith.science/api/pith-number/WFR4IYYOT5XNVGABHCV5DSY6QT/graph.json","fetch_events":"https://pith.science/api/pith-number/WFR4IYYOT5XNVGABHCV5DSY6QT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFR4IYYOT5XNVGABHCV5DSY6QT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFR4IYYOT5XNVGABHCV5DSY6QT/action/storage_attestation","attest_author":"https://pith.science/pith/WFR4IYYOT5XNVGABHCV5DSY6QT/action/author_attestation","sign_citation":"https://pith.science/pith/WFR4IYYOT5XNVGABHCV5DSY6QT/action/citation_signature","submit_replication":"https://pith.science/pith/WFR4IYYOT5XNVGABHCV5DSY6QT/action/replication_record"}},"created_at":"2026-07-05T11:17:48.396763+00:00","updated_at":"2026-07-05T11:17:48.396763+00:00"}