{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4H27LC2B2KWLHEOFE3XYX5LNUV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ec95aaf93ed5b15f135e3e55c807771a55599544960e56b0443d698ad184ce6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T09:10:43Z","title_canon_sha256":"d9d153b0e9c78820af7385e1513a33a1a3dc8d6eae7b63c7cce7d3954511a297"},"schema_version":"1.0","source":{"id":"2607.22114","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22114","created_at":"2026-07-27T01:20:48Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22114v1","created_at":"2026-07-27T01:20:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22114","created_at":"2026-07-27T01:20:48Z"},{"alias_kind":"pith_short_12","alias_value":"4H27LC2B2KWL","created_at":"2026-07-27T01:20:48Z"},{"alias_kind":"pith_short_16","alias_value":"4H27LC2B2KWLHEOF","created_at":"2026-07-27T01:20:48Z"},{"alias_kind":"pith_short_8","alias_value":"4H27LC2B","created_at":"2026-07-27T01:20:48Z"}],"graph_snapshots":[{"event_id":"sha256:50b0b142e651275cb73578b3fd97885d0c9dada52e9c372e6972f64a79651f0c","target":"graph","created_at":"2026-07-27T01:20:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.22114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"A. Aldo Faisal, Jinpei Han, Joshua Placidi, Marek Rei, Yuxuan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T09:10:43Z","title":"Pretraining EHR Foundation Models with Patient-Aware Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22114","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f8d225156723686e42da0c72ece1ce2521f6bff564c763736799c4880806ecfc","target":"record","created_at":"2026-07-27T01:20:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ec95aaf93ed5b15f135e3e55c807771a55599544960e56b0443d698ad184ce6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T09:10:43Z","title_canon_sha256":"d9d153b0e9c78820af7385e1513a33a1a3dc8d6eae7b63c7cce7d3954511a297"},"schema_version":"1.0","source":{"id":"2607.22114","kind":"arxiv","version":1}},"canonical_sha256":"e1f5f58b41d2acb391c526ef8bf56da568c17e8d7663bda7f06b76635d314360","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1f5f58b41d2acb391c526ef8bf56da568c17e8d7663bda7f06b76635d314360","first_computed_at":"2026-07-27T01:20:48.904842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:20:48.904842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XhY80Yo97ba+oHwud5x6+lFBALAkgUjW69L8x8/eyqczNGlblPAOGwZypnS6grlrSw0612DYcZ+gH9X9+syRDg==","signature_status":"signed_v1","signed_at":"2026-07-27T01:20:48.905792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22114","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8d225156723686e42da0c72ece1ce2521f6bff564c763736799c4880806ecfc","sha256:50b0b142e651275cb73578b3fd97885d0c9dada52e9c372e6972f64a79651f0c"],"state_sha256":"5140708ce384c8dc19900b634238ffa962ba9b2d26c44e4913dc7eff6b736864"}