{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OWGSGDIOJHHOOJSMWSVVUJIIOQ","short_pith_number":"pith:OWGSGDIO","schema_version":"1.0","canonical_sha256":"758d230d0e49cee7264cb4ab5a25087439db944fb1996a16533711ff36040fbe","source":{"kind":"arxiv","id":"2212.06040","version":1},"attestation_state":"computed","paper":{"title":"Semantic Decomposition Improves Learning of Large Language Models on EHR Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna L. Decker, David A. Bloore, Jacob Oppenheim, Romane Gauriau","submitted_at":"2022-11-14T14:59:16Z","abstract_excerpt":"Electronic health records (EHR) are widely believed to hold a profusion of actionable insights, encrypted in an irregular, semi-structured format, amidst a loud noise background. To simplify learning patterns of health and disease, medical codes in EHR can be decomposed into semantic units connected by hierarchical graphs. Building on earlier synergy between Bidirectional Encoder Representations from Transformers (BERT) and Graph Attention Networks (GAT), we present H-BERT, which ingests complete graph tree expansions of hierarchical medical codes as opposed to only ingesting the leaves and pu"},"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":"2212.06040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T14:59:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"94863def68de53145cc3191eae18f2171490f23633db9c2e93436b30ddbe69a1","abstract_canon_sha256":"4de488cc3e18cb4032707d82208f6a30a22d5ed8d0178fdcd24e3961255377d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:22.008066Z","signature_b64":"JTA8WF/oBeryVkxKedIwSRihvHO6K4zZABNT2O76GJuDZstR7HXquCtDq+M20cyLoq0yEqx2awpS5pFGcYfNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"758d230d0e49cee7264cb4ab5a25087439db944fb1996a16533711ff36040fbe","last_reissued_at":"2026-07-05T05:24:22.007666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:22.007666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Decomposition Improves Learning of Large Language Models on EHR Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna L. Decker, David A. Bloore, Jacob Oppenheim, Romane Gauriau","submitted_at":"2022-11-14T14:59:16Z","abstract_excerpt":"Electronic health records (EHR) are widely believed to hold a profusion of actionable insights, encrypted in an irregular, semi-structured format, amidst a loud noise background. To simplify learning patterns of health and disease, medical codes in EHR can be decomposed into semantic units connected by hierarchical graphs. Building on earlier synergy between Bidirectional Encoder Representations from Transformers (BERT) and Graph Attention Networks (GAT), we present H-BERT, which ingests complete graph tree expansions of hierarchical medical codes as opposed to only ingesting the leaves and pu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06040","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/2212.06040/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":"2212.06040","created_at":"2026-07-05T05:24:22.007732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.06040v1","created_at":"2026-07-05T05:24:22.007732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06040","created_at":"2026-07-05T05:24:22.007732+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWGSGDIOJHHO","created_at":"2026-07-05T05:24:22.007732+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWGSGDIOJHHOOJSM","created_at":"2026-07-05T05:24:22.007732+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWGSGDIO","created_at":"2026-07-05T05:24:22.007732+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/OWGSGDIOJHHOOJSMWSVVUJIIOQ","json":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ.json","graph_json":"https://pith.science/api/pith-number/OWGSGDIOJHHOOJSMWSVVUJIIOQ/graph.json","events_json":"https://pith.science/api/pith-number/OWGSGDIOJHHOOJSMWSVVUJIIOQ/events.json","paper":"https://pith.science/paper/OWGSGDIO"},"agent_actions":{"view_html":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ","download_json":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ.json","view_paper":"https://pith.science/paper/OWGSGDIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.06040&json=true","fetch_graph":"https://pith.science/api/pith-number/OWGSGDIOJHHOOJSMWSVVUJIIOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/OWGSGDIOJHHOOJSMWSVVUJIIOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/action/storage_attestation","attest_author":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/action/author_attestation","sign_citation":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/action/citation_signature","submit_replication":"https://pith.science/pith/OWGSGDIOJHHOOJSMWSVVUJIIOQ/action/replication_record"}},"created_at":"2026-07-05T05:24:22.007732+00:00","updated_at":"2026-07-05T05:24:22.007732+00:00"}