{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ERR7XTZORTWGMPCBFJRLJWDZT3","short_pith_number":"pith:ERR7XTZO","schema_version":"1.0","canonical_sha256":"2463fbcf2e8cec663c412a62b4d8799eddd578658a273988eab9ca9aede0e69a","source":{"kind":"arxiv","id":"2404.15201","version":4},"attestation_state":"computed","paper":{"title":"CORE-BEHRT: A Carefully Optimized and Rigorously Evaluated BEHRT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Espen Jimenez-Solem, Kiril Vadimovic Klein, Mads Nielsen, Martin Sillesen, Mikkel Odgaard, Sanne M{\\o}ller Thysen","submitted_at":"2024-04-23T16:35:59Z","abstract_excerpt":"The widespread adoption of Electronic Health Records (EHR) has significantly increased the amount of available healthcare data. This has allowed models inspired by Natural Language Processing (NLP) and Computer Vision, which scale exceptionally well, to be used in EHR research. Particularly, BERT-based models have surged in popularity following the release of BEHRT and Med-BERT. Subsequent models have largely built on these foundations despite the fundamental design choices of these pioneering models remaining underexplored. Through incremental optimization, we study BERT-based EHR modeling an"},"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":"2404.15201","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T16:35:59Z","cross_cats_sorted":[],"title_canon_sha256":"68f189a2cf391356edfdefb01ea667baf23a56eae452a03fcf84eb788edac0e7","abstract_canon_sha256":"4c13a4c42acd9689b34796ea33d0f82472a6d1b981169acc77dc67796aa33e43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:09.026600Z","signature_b64":"tl1a2NKBzN0X739l7+d2rOmSIpcpewq3J47o8IIWxUMEvIhbZXvvKyivL35nnZBfKdtlkd/0s1b0JV8eRrAtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2463fbcf2e8cec663c412a62b4d8799eddd578658a273988eab9ca9aede0e69a","last_reissued_at":"2026-07-05T09:19:09.026109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:09.026109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CORE-BEHRT: A Carefully Optimized and Rigorously Evaluated BEHRT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Espen Jimenez-Solem, Kiril Vadimovic Klein, Mads Nielsen, Martin Sillesen, Mikkel Odgaard, Sanne M{\\o}ller Thysen","submitted_at":"2024-04-23T16:35:59Z","abstract_excerpt":"The widespread adoption of Electronic Health Records (EHR) has significantly increased the amount of available healthcare data. This has allowed models inspired by Natural Language Processing (NLP) and Computer Vision, which scale exceptionally well, to be used in EHR research. Particularly, BERT-based models have surged in popularity following the release of BEHRT and Med-BERT. Subsequent models have largely built on these foundations despite the fundamental design choices of these pioneering models remaining underexplored. Through incremental optimization, we study BERT-based EHR modeling an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15201","kind":"arxiv","version":4},"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/2404.15201/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":"2404.15201","created_at":"2026-07-05T09:19:09.026169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15201v4","created_at":"2026-07-05T09:19:09.026169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15201","created_at":"2026-07-05T09:19:09.026169+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERR7XTZORTWG","created_at":"2026-07-05T09:19:09.026169+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERR7XTZORTWGMPCB","created_at":"2026-07-05T09:19:09.026169+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERR7XTZO","created_at":"2026-07-05T09:19:09.026169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17765","citing_title":"AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00520","citing_title":"NEST: Nested Event Stream Transformer for Sequences of Multisets","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04175","citing_title":"Uncertainty-Aware Foundation Models for Clinical Data","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12335","citing_title":"EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08685","citing_title":"Event Fields: Learning Latent Event Structure for Waveform Foundation Models","ref_index":23,"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":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERR7XTZORTWGMPCBFJRLJWDZT3","json":"https://pith.science/pith/ERR7XTZORTWGMPCBFJRLJWDZT3.json","graph_json":"https://pith.science/api/pith-number/ERR7XTZORTWGMPCBFJRLJWDZT3/graph.json","events_json":"https://pith.science/api/pith-number/ERR7XTZORTWGMPCBFJRLJWDZT3/events.json","paper":"https://pith.science/paper/ERR7XTZO"},"agent_actions":{"view_html":"https://pith.science/pith/ERR7XTZORTWGMPCBFJRLJWDZT3","download_json":"https://pith.science/pith/ERR7XTZORTWGMPCBFJRLJWDZT3.json","view_paper":"https://pith.science/paper/ERR7XTZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15201&json=true","fetch_graph":"https://pith.science/api/pith-number/ERR7XTZORTWGMPCBFJRLJWDZT3/graph.json","fetch_events":"https://pith.science/api/pith-number/ERR7XTZORTWGMPCBFJRLJWDZT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERR7XTZORTWGMPCBFJRLJWDZT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERR7XTZORTWGMPCBFJRLJWDZT3/action/storage_attestation","attest_author":"https://pith.science/pith/ERR7XTZORTWGMPCBFJRLJWDZT3/action/author_attestation","sign_citation":"https://pith.science/pith/ERR7XTZORTWGMPCBFJRLJWDZT3/action/citation_signature","submit_replication":"https://pith.science/pith/ERR7XTZORTWGMPCBFJRLJWDZT3/action/replication_record"}},"created_at":"2026-07-05T09:19:09.026169+00:00","updated_at":"2026-07-05T09:19:09.026169+00:00"}