{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HZHPOIUPY227572XWB74S3FWWM","short_pith_number":"pith:HZHPOIUP","schema_version":"1.0","canonical_sha256":"3e4ef7228fc6b5feff57b07fc96cb6b33aa20f27e1048c972ecdab81fb8a433e","source":{"kind":"arxiv","id":"2504.10422","version":1},"attestation_state":"computed","paper":{"title":"Foundation models for electronic health records: representation dynamics and transferability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bashar Ramadan, Brett K. Beaulieu-Jones, Juan C. Rojas, Kaveri Chhikara, Michael C. Burkhart, William F. Parker, Zewei Liao","submitted_at":"2025-04-14T17:09:05Z","abstract_excerpt":"Foundation models (FMs) trained on electronic health records (EHRs) have shown strong performance on a range of clinical prediction tasks. However, adapting these models to local health systems remains challenging due to limited data availability and resource constraints. In this study, we investigated what these models learn and evaluated the transferability of an FM trained on MIMIC-IV to an institutional EHR dataset at the University of Chicago Medical Center. We assessed their ability to identify outlier patients and examined representation-space patient trajectories in relation to future "},"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":"2504.10422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-14T17:09:05Z","cross_cats_sorted":[],"title_canon_sha256":"9b304d52f71329117c7d86897ba5d1707d01722945e1f672decbee87085bf54c","abstract_canon_sha256":"f0a7f50e011028304c245a1b59b5573860f501c0d6dd8df64d26712e269171b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:00.111661Z","signature_b64":"dVzSTMU3GmfMxRUq50BOmAxt2IaDL/sdCCfu1kFXhFUaHjDn5aP9tZ24Hrs3UYNe3+4S/yNxKVhF1zkavTo9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e4ef7228fc6b5feff57b07fc96cb6b33aa20f27e1048c972ecdab81fb8a433e","last_reissued_at":"2026-07-05T10:49:00.111186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:00.111186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundation models for electronic health records: representation dynamics and transferability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bashar Ramadan, Brett K. Beaulieu-Jones, Juan C. Rojas, Kaveri Chhikara, Michael C. Burkhart, William F. Parker, Zewei Liao","submitted_at":"2025-04-14T17:09:05Z","abstract_excerpt":"Foundation models (FMs) trained on electronic health records (EHRs) have shown strong performance on a range of clinical prediction tasks. However, adapting these models to local health systems remains challenging due to limited data availability and resource constraints. In this study, we investigated what these models learn and evaluated the transferability of an FM trained on MIMIC-IV to an institutional EHR dataset at the University of Chicago Medical Center. We assessed their ability to identify outlier patients and examined representation-space patient trajectories in relation to future "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10422","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/2504.10422/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":"2504.10422","created_at":"2026-07-05T10:49:00.111244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10422v1","created_at":"2026-07-05T10:49:00.111244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10422","created_at":"2026-07-05T10:49:00.111244+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZHPOIUPY227","created_at":"2026-07-05T10:49:00.111244+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZHPOIUPY227572X","created_at":"2026-07-05T10:49:00.111244+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZHPOIUP","created_at":"2026-07-05T10:49:00.111244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10840","citing_title":"Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17765","citing_title":"AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04175","citing_title":"Uncertainty-Aware Foundation Models for Clinical Data","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10840","citing_title":"Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08685","citing_title":"Event Fields: Learning Latent Event Structure for Waveform Foundation Models","ref_index":2,"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":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10840","citing_title":"Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16775","citing_title":"Representation Before Training: A Fixed-Budget Benchmark for Generative Medical Event Models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZHPOIUPY227572XWB74S3FWWM","json":"https://pith.science/pith/HZHPOIUPY227572XWB74S3FWWM.json","graph_json":"https://pith.science/api/pith-number/HZHPOIUPY227572XWB74S3FWWM/graph.json","events_json":"https://pith.science/api/pith-number/HZHPOIUPY227572XWB74S3FWWM/events.json","paper":"https://pith.science/paper/HZHPOIUP"},"agent_actions":{"view_html":"https://pith.science/pith/HZHPOIUPY227572XWB74S3FWWM","download_json":"https://pith.science/pith/HZHPOIUPY227572XWB74S3FWWM.json","view_paper":"https://pith.science/paper/HZHPOIUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10422&json=true","fetch_graph":"https://pith.science/api/pith-number/HZHPOIUPY227572XWB74S3FWWM/graph.json","fetch_events":"https://pith.science/api/pith-number/HZHPOIUPY227572XWB74S3FWWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZHPOIUPY227572XWB74S3FWWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZHPOIUPY227572XWB74S3FWWM/action/storage_attestation","attest_author":"https://pith.science/pith/HZHPOIUPY227572XWB74S3FWWM/action/author_attestation","sign_citation":"https://pith.science/pith/HZHPOIUPY227572XWB74S3FWWM/action/citation_signature","submit_replication":"https://pith.science/pith/HZHPOIUPY227572XWB74S3FWWM/action/replication_record"}},"created_at":"2026-07-05T10:49:00.111244+00:00","updated_at":"2026-07-05T10:49:00.111244+00:00"}