{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KAXOUSY4EAZNIRXZOZSLUA6K4J","short_pith_number":"pith:KAXOUSY4","canonical_record":{"source":{"id":"2507.00574","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T08:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"9c28e147e88699ac0e940aa6d3997b517d6cc160c4135b9786bfd8ad3eddc5dc","abstract_canon_sha256":"80a2cefb41da6eeee76e60f2338db4d7191eb83a94586efae50299213d8e9dd3"},"schema_version":"1.0"},"canonical_sha256":"502eea4b1c2032d446f97664ba03cae27623704c2cdeaacc11fd1095c0fb67da","source":{"kind":"arxiv","id":"2507.00574","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00574","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00574v1","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00574","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"KAXOUSY4EAZN","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"KAXOUSY4EAZNIRXZ","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"KAXOUSY4","created_at":"2026-07-05T11:30:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KAXOUSY4EAZNIRXZOZSLUA6K4J","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00574","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T08:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"9c28e147e88699ac0e940aa6d3997b517d6cc160c4135b9786bfd8ad3eddc5dc","abstract_canon_sha256":"80a2cefb41da6eeee76e60f2338db4d7191eb83a94586efae50299213d8e9dd3"},"schema_version":"1.0"},"canonical_sha256":"502eea4b1c2032d446f97664ba03cae27623704c2cdeaacc11fd1095c0fb67da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:11.051779Z","signature_b64":"EhP/YrMOd+RePzcnajmJKB9FwuvRH11gbnZC0rwQnT4C3j909ra2M1A33qSzzbZMDxQhPoL4iDOmTXqdbpBnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"502eea4b1c2032d446f97664ba03cae27623704c2cdeaacc11fd1095c0fb67da","last_reissued_at":"2026-07-05T11:30:11.051290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:11.051290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00574","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"deLfreqWKF2yoOr5JYHilV8GK8jA+OjTI3BCryA01EBawweDSzISlPi//UQSyOA0jQymFaWjB6OVab15HmDXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:03:07.574025Z"},"content_sha256":"aabfcb68f8470b5e3783b472d4ba285e48b70fd3e73360c853db2ddda2d20dd9","schema_version":"1.0","event_id":"sha256:aabfcb68f8470b5e3783b472d4ba285e48b70fd3e73360c853db2ddda2d20dd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KAXOUSY4EAZNIRXZOZSLUA6K4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Foundation Models for Clinical Records at Health System Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cem M. Deniz, Haresh Rengaraj Rajamohan, Kyunghyun Cho, Long Chen, Narges Razavian, Shih-Lun Huang, Weicheng Zhu, Xiang Gao","submitted_at":"2025-07-01T08:52:33Z","abstract_excerpt":"Large-scale pretraining has transformed modeling of language and other data types, but its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present a novel generative pretraining strategy for sequential EHR data using next-visit event prediction. Our model learns to autoregressively generate various tokenized clinical events for the next visit based on patient history and inherently handles the joint prediction of heterogeneous data types. Additionally, we introduce regularization on predicting repeated events and highlight a key pitfall in EHR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00574","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/2507.00574/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EKCmDmT3qWWjIgJAi3MKbz0YsDCA8Ui7yWPeA+q9ptidsgj2Z6BvWmNqwbule5j+gN+o0p5l1S8j9Ur5FYJICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:03:07.574536Z"},"content_sha256":"0b5fa80226d269b52e72bf5266f0ac9eeae7df8964629cba8ad4e4f3a9c4b0ec","schema_version":"1.0","event_id":"sha256:0b5fa80226d269b52e72bf5266f0ac9eeae7df8964629cba8ad4e4f3a9c4b0ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KAXOUSY4EAZNIRXZOZSLUA6K4J/bundle.json","state_url":"https://pith.science/pith/KAXOUSY4EAZNIRXZOZSLUA6K4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KAXOUSY4EAZNIRXZOZSLUA6K4J/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T00:03:07Z","links":{"resolver":"https://pith.science/pith/KAXOUSY4EAZNIRXZOZSLUA6K4J","bundle":"https://pith.science/pith/KAXOUSY4EAZNIRXZOZSLUA6K4J/bundle.json","state":"https://pith.science/pith/KAXOUSY4EAZNIRXZOZSLUA6K4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KAXOUSY4EAZNIRXZOZSLUA6K4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KAXOUSY4EAZNIRXZOZSLUA6K4J","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":"80a2cefb41da6eeee76e60f2338db4d7191eb83a94586efae50299213d8e9dd3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T08:52:33Z","title_canon_sha256":"9c28e147e88699ac0e940aa6d3997b517d6cc160c4135b9786bfd8ad3eddc5dc"},"schema_version":"1.0","source":{"id":"2507.00574","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00574","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00574v1","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00574","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"KAXOUSY4EAZN","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"KAXOUSY4EAZNIRXZ","created_at":"2026-07-05T11:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"KAXOUSY4","created_at":"2026-07-05T11:30:11Z"}],"graph_snapshots":[{"event_id":"sha256:0b5fa80226d269b52e72bf5266f0ac9eeae7df8964629cba8ad4e4f3a9c4b0ec","target":"graph","created_at":"2026-07-05T11:30:11Z","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/2507.00574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pretraining has transformed modeling of language and other data types, but its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present a novel generative pretraining strategy for sequential EHR data using next-visit event prediction. Our model learns to autoregressively generate various tokenized clinical events for the next visit based on patient history and inherently handles the joint prediction of heterogeneous data types. Additionally, we introduce regularization on predicting repeated events and highlight a key pitfall in EHR","authors_text":"Cem M. Deniz, Haresh Rengaraj Rajamohan, Kyunghyun Cho, Long Chen, Narges Razavian, Shih-Lun Huang, Weicheng Zhu, Xiang Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T08:52:33Z","title":"Foundation Models for Clinical Records at Health System Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00574","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:aabfcb68f8470b5e3783b472d4ba285e48b70fd3e73360c853db2ddda2d20dd9","target":"record","created_at":"2026-07-05T11:30:11Z","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":"80a2cefb41da6eeee76e60f2338db4d7191eb83a94586efae50299213d8e9dd3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T08:52:33Z","title_canon_sha256":"9c28e147e88699ac0e940aa6d3997b517d6cc160c4135b9786bfd8ad3eddc5dc"},"schema_version":"1.0","source":{"id":"2507.00574","kind":"arxiv","version":1}},"canonical_sha256":"502eea4b1c2032d446f97664ba03cae27623704c2cdeaacc11fd1095c0fb67da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"502eea4b1c2032d446f97664ba03cae27623704c2cdeaacc11fd1095c0fb67da","first_computed_at":"2026-07-05T11:30:11.051290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:11.051290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EhP/YrMOd+RePzcnajmJKB9FwuvRH11gbnZC0rwQnT4C3j909ra2M1A33qSzzbZMDxQhPoL4iDOmTXqdbpBnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:11.051779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00574","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aabfcb68f8470b5e3783b472d4ba285e48b70fd3e73360c853db2ddda2d20dd9","sha256:0b5fa80226d269b52e72bf5266f0ac9eeae7df8964629cba8ad4e4f3a9c4b0ec"],"state_sha256":"1209ba442395dd4e4a932ba4e61f5e244713de846c131868171129401543ae40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2qltCZGnKQSK8g3LH3663IMSgS9ZunjYPjK9Aod/pR2GCUMsWcREHYJyZJc2BUebklJxitUBE06/NJJqc9nDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:03:07.579580Z","bundle_sha256":"de3b3bfcf926add5b8701d5fa8bce9bd506316581e12b6bd80708ceb5ea25875"}}