{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JCMNO5TLSMGGNIDYV6MYH6M3KT","short_pith_number":"pith:JCMNO5TL","schema_version":"1.0","canonical_sha256":"4898d7766b930c66a078af9983f99b54ec9969bf089b13fbb9442ae1512c2493","source":{"kind":"arxiv","id":"2509.03643","version":2},"attestation_state":"computed","paper":{"title":"CEHR-XGPT: A Scalable Multi-Task Foundation Model for Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Pang, Jiheum Park, Karthik Natarajan, Krishna S. Kalluri, Nishanth Parameshwar Pavinkurve, No\\'emie Elhadad, Shalmali Joshi, Xinzhuo Jiang","submitted_at":"2025-09-03T18:50:03Z","abstract_excerpt":"Electronic Health Records (EHRs) provide a rich, longitudinal view of patient health and hold significant potential for advancing clinical decision support, risk prediction, and data-driven healthcare research. However, most artificial intelligence (AI) models for EHRs are designed for narrow, single-purpose tasks, limiting their generalizability and utility in real-world settings. Here, we present CEHR-XGPT, a general-purpose foundation model for EHR data that unifies three essential capabilities - feature representation, zero-shot prediction, and synthetic data generation - within a single a"},"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":"2509.03643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T18:50:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8e1422e0abd529309def356827e5f68aad7034b4c6a86815d1c8bc1a6249f1a3","abstract_canon_sha256":"c40475400b00754cb4b5d34cc26b60286e7af3158a2d1b8109edc91315852412"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:22.581808Z","signature_b64":"bMH6e143NpS5jRIXiLMf0eHv4LSV4/qGWxpDs+wUjnoYMG1AMWRoP+dx5rAMxUWLUg+eka/uWU4+Diu2WpfcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4898d7766b930c66a078af9983f99b54ec9969bf089b13fbb9442ae1512c2493","last_reissued_at":"2026-07-05T12:05:22.581299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:22.581299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CEHR-XGPT: A Scalable Multi-Task Foundation Model for Electronic Health Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Pang, Jiheum Park, Karthik Natarajan, Krishna S. Kalluri, Nishanth Parameshwar Pavinkurve, No\\'emie Elhadad, Shalmali Joshi, Xinzhuo Jiang","submitted_at":"2025-09-03T18:50:03Z","abstract_excerpt":"Electronic Health Records (EHRs) provide a rich, longitudinal view of patient health and hold significant potential for advancing clinical decision support, risk prediction, and data-driven healthcare research. However, most artificial intelligence (AI) models for EHRs are designed for narrow, single-purpose tasks, limiting their generalizability and utility in real-world settings. Here, we present CEHR-XGPT, a general-purpose foundation model for EHR data that unifies three essential capabilities - feature representation, zero-shot prediction, and synthetic data generation - within a single a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03643","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/2509.03643/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":"2509.03643","created_at":"2026-07-05T12:05:22.581371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03643v2","created_at":"2026-07-05T12:05:22.581371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03643","created_at":"2026-07-05T12:05:22.581371+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCMNO5TLSMGG","created_at":"2026-07-05T12:05:22.581371+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCMNO5TLSMGGNIDY","created_at":"2026-07-05T12:05:22.581371+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCMNO5TL","created_at":"2026-07-05T12:05:22.581371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24102","citing_title":"PORTER: Language-Grounded Event Representations for Portable Structured EHR Foundation Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01391","citing_title":"How Should Transformers Encode Numeric Values in Electronic Health Records?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24562","citing_title":"Scaling Recurrence-aware Foundation Models for Clinical Records via Next-Visit Prediction","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JCMNO5TLSMGGNIDYV6MYH6M3KT","json":"https://pith.science/pith/JCMNO5TLSMGGNIDYV6MYH6M3KT.json","graph_json":"https://pith.science/api/pith-number/JCMNO5TLSMGGNIDYV6MYH6M3KT/graph.json","events_json":"https://pith.science/api/pith-number/JCMNO5TLSMGGNIDYV6MYH6M3KT/events.json","paper":"https://pith.science/paper/JCMNO5TL"},"agent_actions":{"view_html":"https://pith.science/pith/JCMNO5TLSMGGNIDYV6MYH6M3KT","download_json":"https://pith.science/pith/JCMNO5TLSMGGNIDYV6MYH6M3KT.json","view_paper":"https://pith.science/paper/JCMNO5TL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03643&json=true","fetch_graph":"https://pith.science/api/pith-number/JCMNO5TLSMGGNIDYV6MYH6M3KT/graph.json","fetch_events":"https://pith.science/api/pith-number/JCMNO5TLSMGGNIDYV6MYH6M3KT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCMNO5TLSMGGNIDYV6MYH6M3KT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCMNO5TLSMGGNIDYV6MYH6M3KT/action/storage_attestation","attest_author":"https://pith.science/pith/JCMNO5TLSMGGNIDYV6MYH6M3KT/action/author_attestation","sign_citation":"https://pith.science/pith/JCMNO5TLSMGGNIDYV6MYH6M3KT/action/citation_signature","submit_replication":"https://pith.science/pith/JCMNO5TLSMGGNIDYV6MYH6M3KT/action/replication_record"}},"created_at":"2026-07-05T12:05:22.581371+00:00","updated_at":"2026-07-05T12:05:22.581371+00:00"}