{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:STFRLY5QKRXLO663OF76DBNL2X","short_pith_number":"pith:STFRLY5Q","schema_version":"1.0","canonical_sha256":"94cb15e3b0546eb77bdb717fe185abd5d3d96a9fa1680f61d12252b2fbcfbf0a","source":{"kind":"arxiv","id":"2602.00541","version":2},"attestation_state":"computed","paper":{"title":"One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aparajita Kashyap, Chao Pang, Shalmali Joshi, Simon A. Lee, Vincent Jeanselme, Xinzhuo Jiang, Yanwei Li, Yuta Kobayashi, Zilin Jing","submitted_at":"2026-01-31T06:15:46Z","abstract_excerpt":"Clinical events captured in Electronic Health Records (EHR) are irregularly sampled and may consist of a mixture of discrete events and numerical measurements, such as laboratory values or treatment dosages. The sequential nature of EHR, analogous to natural language, has motivated the use of next-token prediction to train prior EHR Foundation Models (FMs) over events. However, this training fails to capture the full structure of EHR. When a given event occurs must be captured, but the event value (abnormal lab) also modulates the likelihood of other clinical events. Most existing EHR FMs do n"},"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":"2602.00541","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-31T06:15:46Z","cross_cats_sorted":[],"title_canon_sha256":"68c44cf8e6094fbd3508178ab3634981539e29044923b31b0e9679d056c966f2","abstract_canon_sha256":"b26d5d9f1e1a7b3e36e2e0ed12bd61cc20a42bd302671c90bb2e1c39d4513c85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:57.351040Z","signature_b64":"PADIjPgEFbo04S7/PTwuAV3OwC3+E8ck+wUDJnFL/wgCOugA2RsT39ezs7iXmqOHTWd9bozStlN0whn6x2yzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94cb15e3b0546eb77bdb717fe185abd5d3d96a9fa1680f61d12252b2fbcfbf0a","last_reissued_at":"2026-06-08T01:03:57.350343Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:57.350343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aparajita Kashyap, Chao Pang, Shalmali Joshi, Simon A. Lee, Vincent Jeanselme, Xinzhuo Jiang, Yanwei Li, Yuta Kobayashi, Zilin Jing","submitted_at":"2026-01-31T06:15:46Z","abstract_excerpt":"Clinical events captured in Electronic Health Records (EHR) are irregularly sampled and may consist of a mixture of discrete events and numerical measurements, such as laboratory values or treatment dosages. The sequential nature of EHR, analogous to natural language, has motivated the use of next-token prediction to train prior EHR Foundation Models (FMs) over events. However, this training fails to capture the full structure of EHR. When a given event occurs must be captured, but the event value (abnormal lab) also modulates the likelihood of other clinical events. Most existing EHR FMs do n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00541","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/2602.00541/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":"2602.00541","created_at":"2026-06-08T01:03:57.350434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.00541v2","created_at":"2026-06-08T01:03:57.350434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00541","created_at":"2026-06-08T01:03:57.350434+00:00"},{"alias_kind":"pith_short_12","alias_value":"STFRLY5QKRXL","created_at":"2026-06-08T01:03:57.350434+00:00"},{"alias_kind":"pith_short_16","alias_value":"STFRLY5QKRXLO663","created_at":"2026-06-08T01:03:57.350434+00:00"},{"alias_kind":"pith_short_8","alias_value":"STFRLY5Q","created_at":"2026-06-08T01:03:57.350434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17765","citing_title":"AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STFRLY5QKRXLO663OF76DBNL2X","json":"https://pith.science/pith/STFRLY5QKRXLO663OF76DBNL2X.json","graph_json":"https://pith.science/api/pith-number/STFRLY5QKRXLO663OF76DBNL2X/graph.json","events_json":"https://pith.science/api/pith-number/STFRLY5QKRXLO663OF76DBNL2X/events.json","paper":"https://pith.science/paper/STFRLY5Q"},"agent_actions":{"view_html":"https://pith.science/pith/STFRLY5QKRXLO663OF76DBNL2X","download_json":"https://pith.science/pith/STFRLY5QKRXLO663OF76DBNL2X.json","view_paper":"https://pith.science/paper/STFRLY5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.00541&json=true","fetch_graph":"https://pith.science/api/pith-number/STFRLY5QKRXLO663OF76DBNL2X/graph.json","fetch_events":"https://pith.science/api/pith-number/STFRLY5QKRXLO663OF76DBNL2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STFRLY5QKRXLO663OF76DBNL2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STFRLY5QKRXLO663OF76DBNL2X/action/storage_attestation","attest_author":"https://pith.science/pith/STFRLY5QKRXLO663OF76DBNL2X/action/author_attestation","sign_citation":"https://pith.science/pith/STFRLY5QKRXLO663OF76DBNL2X/action/citation_signature","submit_replication":"https://pith.science/pith/STFRLY5QKRXLO663OF76DBNL2X/action/replication_record"}},"created_at":"2026-06-08T01:03:57.350434+00:00","updated_at":"2026-06-08T01:03:57.350434+00:00"}