{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EXDI54D5MZODKHG4CMABEEEVQE","short_pith_number":"pith:EXDI54D5","schema_version":"1.0","canonical_sha256":"25c68ef07d665c351cdc1300121095810083d8cd712bba37989f2729b1956910","source":{"kind":"arxiv","id":"2505.22964","version":2},"attestation_state":"computed","paper":{"title":"Exploring Scaling Laws for EHR Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cliff Wong, Hoifung Poon, Naoto Usuyama, Qin Liu, Sheng Zhang, Tristan Naumann","submitted_at":"2025-05-29T01:05:11Z","abstract_excerpt":"The emergence of scaling laws has profoundly shaped the development of large language models (LLMs), enabling predictable performance gains through systematic increases in model size, dataset volume, and compute. Yet, these principles remain largely unexplored in the context of electronic health records (EHRs) -- a rich, sequential, and globally abundant data source that differs structurally from natural language. In this work, we present the first empirical investigation of scaling laws for EHR foundation models. By training transformer architectures on patient timeline data from the MIMIC-IV"},"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":"2505.22964","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T01:05:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3fce4b9272dea873f8cfb075358396dc45dd084b56e663de880142769c394909","abstract_canon_sha256":"1d829985061d375bc0da2273c2c3612cfc86d3ea7dd5817cca04f9eeedae26e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:03.852676Z","signature_b64":"IvAtVoNRDm5CY4Ez4tyb+65TyY8gshutASxjE4m0ADYYQFvCHTmKUdeccwze1TkzSoFK0veMKLhz/RR6pfKaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25c68ef07d665c351cdc1300121095810083d8cd712bba37989f2729b1956910","last_reissued_at":"2026-07-05T11:53:03.852216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:03.852216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Scaling Laws for EHR Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cliff Wong, Hoifung Poon, Naoto Usuyama, Qin Liu, Sheng Zhang, Tristan Naumann","submitted_at":"2025-05-29T01:05:11Z","abstract_excerpt":"The emergence of scaling laws has profoundly shaped the development of large language models (LLMs), enabling predictable performance gains through systematic increases in model size, dataset volume, and compute. Yet, these principles remain largely unexplored in the context of electronic health records (EHRs) -- a rich, sequential, and globally abundant data source that differs structurally from natural language. In this work, we present the first empirical investigation of scaling laws for EHR foundation models. By training transformer architectures on patient timeline data from the MIMIC-IV"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22964","kind":"arxiv","version":2},"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/2505.22964/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":"2505.22964","created_at":"2026-07-05T11:53:03.852270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22964v2","created_at":"2026-07-05T11:53:03.852270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22964","created_at":"2026-07-05T11:53:03.852270+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXDI54D5MZOD","created_at":"2026-07-05T11:53:03.852270+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXDI54D5MZODKHG4","created_at":"2026-07-05T11:53:03.852270+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXDI54D5","created_at":"2026-07-05T11:53:03.852270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.24562","citing_title":"Scaling Recurrence-aware Foundation Models for Clinical Records via Next-Visit Prediction","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07546","citing_title":"On the Invariance and Generality of Neural Scaling Laws","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10386","citing_title":"TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02740","citing_title":"Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXDI54D5MZODKHG4CMABEEEVQE","json":"https://pith.science/pith/EXDI54D5MZODKHG4CMABEEEVQE.json","graph_json":"https://pith.science/api/pith-number/EXDI54D5MZODKHG4CMABEEEVQE/graph.json","events_json":"https://pith.science/api/pith-number/EXDI54D5MZODKHG4CMABEEEVQE/events.json","paper":"https://pith.science/paper/EXDI54D5"},"agent_actions":{"view_html":"https://pith.science/pith/EXDI54D5MZODKHG4CMABEEEVQE","download_json":"https://pith.science/pith/EXDI54D5MZODKHG4CMABEEEVQE.json","view_paper":"https://pith.science/paper/EXDI54D5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22964&json=true","fetch_graph":"https://pith.science/api/pith-number/EXDI54D5MZODKHG4CMABEEEVQE/graph.json","fetch_events":"https://pith.science/api/pith-number/EXDI54D5MZODKHG4CMABEEEVQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXDI54D5MZODKHG4CMABEEEVQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXDI54D5MZODKHG4CMABEEEVQE/action/storage_attestation","attest_author":"https://pith.science/pith/EXDI54D5MZODKHG4CMABEEEVQE/action/author_attestation","sign_citation":"https://pith.science/pith/EXDI54D5MZODKHG4CMABEEEVQE/action/citation_signature","submit_replication":"https://pith.science/pith/EXDI54D5MZODKHG4CMABEEEVQE/action/replication_record"}},"created_at":"2026-07-05T11:53:03.852270+00:00","updated_at":"2026-07-05T11:53:03.852270+00:00"}