{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4H27LC2B2KWLHEOFE3XYX5LNUV","short_pith_number":"pith:4H27LC2B","schema_version":"1.0","canonical_sha256":"e1f5f58b41d2acb391c526ef8bf56da568c17e8d7663bda7f06b76635d314360","source":{"kind":"arxiv","id":"2607.22114","version":1},"attestation_state":"computed","paper":{"title":"Pretraining EHR Foundation Models with Patient-Aware Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"A. Aldo Faisal, Jinpei Han, Joshua Placidi, Marek Rei, Yuxuan Liu","submitted_at":"2026-07-24T09:10:43Z","abstract_excerpt":"Autoregressive foundation models for electronic health records (EHRs) typically inherit pretraining methods from language modeling, where patient trajectories are concatenated into a single token stream and windows are sampled from that stream. In EHR data, this choice is consequential: windows may mix multiple patients, and patients with longer records contribute more optimization updates, potentially introducing bias. We propose Patient Sampling, a pretraining sequence-construction method that allows us to control how training signal is distributed across patients. We compare this method to "},"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":"2607.22114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T09:10:43Z","cross_cats_sorted":[],"title_canon_sha256":"d9d153b0e9c78820af7385e1513a33a1a3dc8d6eae7b63c7cce7d3954511a297","abstract_canon_sha256":"ec95aaf93ed5b15f135e3e55c807771a55599544960e56b0443d698ad184ce6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:48.905792Z","signature_b64":"XhY80Yo97ba+oHwud5x6+lFBALAkgUjW69L8x8/eyqczNGlblPAOGwZypnS6grlrSw0612DYcZ+gH9X9+syRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1f5f58b41d2acb391c526ef8bf56da568c17e8d7663bda7f06b76635d314360","last_reissued_at":"2026-07-27T01:20:48.904842Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:48.904842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pretraining EHR Foundation Models with Patient-Aware Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"A. Aldo Faisal, Jinpei Han, Joshua Placidi, Marek Rei, Yuxuan Liu","submitted_at":"2026-07-24T09:10:43Z","abstract_excerpt":"Autoregressive foundation models for electronic health records (EHRs) typically inherit pretraining methods from language modeling, where patient trajectories are concatenated into a single token stream and windows are sampled from that stream. In EHR data, this choice is consequential: windows may mix multiple patients, and patients with longer records contribute more optimization updates, potentially introducing bias. We propose Patient Sampling, a pretraining sequence-construction method that allows us to control how training signal is distributed across patients. We compare this method to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22114","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/2607.22114/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":"2607.22114","created_at":"2026-07-27T01:20:48.905323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22114v1","created_at":"2026-07-27T01:20:48.905323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22114","created_at":"2026-07-27T01:20:48.905323+00:00"},{"alias_kind":"pith_short_12","alias_value":"4H27LC2B2KWL","created_at":"2026-07-27T01:20:48.905323+00:00"},{"alias_kind":"pith_short_16","alias_value":"4H27LC2B2KWLHEOF","created_at":"2026-07-27T01:20:48.905323+00:00"},{"alias_kind":"pith_short_8","alias_value":"4H27LC2B","created_at":"2026-07-27T01:20:48.905323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4H27LC2B2KWLHEOFE3XYX5LNUV","json":"https://pith.science/pith/4H27LC2B2KWLHEOFE3XYX5LNUV.json","graph_json":"https://pith.science/api/pith-number/4H27LC2B2KWLHEOFE3XYX5LNUV/graph.json","events_json":"https://pith.science/api/pith-number/4H27LC2B2KWLHEOFE3XYX5LNUV/events.json","paper":"https://pith.science/paper/4H27LC2B"},"agent_actions":{"view_html":"https://pith.science/pith/4H27LC2B2KWLHEOFE3XYX5LNUV","download_json":"https://pith.science/pith/4H27LC2B2KWLHEOFE3XYX5LNUV.json","view_paper":"https://pith.science/paper/4H27LC2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22114&json=true","fetch_graph":"https://pith.science/api/pith-number/4H27LC2B2KWLHEOFE3XYX5LNUV/graph.json","fetch_events":"https://pith.science/api/pith-number/4H27LC2B2KWLHEOFE3XYX5LNUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4H27LC2B2KWLHEOFE3XYX5LNUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4H27LC2B2KWLHEOFE3XYX5LNUV/action/storage_attestation","attest_author":"https://pith.science/pith/4H27LC2B2KWLHEOFE3XYX5LNUV/action/author_attestation","sign_citation":"https://pith.science/pith/4H27LC2B2KWLHEOFE3XYX5LNUV/action/citation_signature","submit_replication":"https://pith.science/pith/4H27LC2B2KWLHEOFE3XYX5LNUV/action/replication_record"}},"created_at":"2026-07-27T01:20:48.905323+00:00","updated_at":"2026-07-27T01:20:48.905323+00:00"}