{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:M2S4UBSJOZTWH6VQYRKD5OMVW5","short_pith_number":"pith:M2S4UBSJ","canonical_record":{"source":{"id":"2304.02169","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-04T23:53:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78038ac2da1c058e2bdf4d2b1d747457047862c5ff4b99c462307abcb9b54f82","abstract_canon_sha256":"76722dff4ed8b881495c7f0e324fd11a9dd8871a758a947e9c099e02e8633458"},"schema_version":"1.0"},"canonical_sha256":"66a5ca0649766763fab0c4543eb995b74a198c5a486740d7ce065688818bacfd","source":{"kind":"arxiv","id":"2304.02169","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02169","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02169v3","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02169","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"M2S4UBSJOZTW","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"M2S4UBSJOZTWH6VQ","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"M2S4UBSJ","created_at":"2026-07-05T07:11:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:M2S4UBSJOZTWH6VQYRKD5OMVW5","target":"record","payload":{"canonical_record":{"source":{"id":"2304.02169","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-04T23:53:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78038ac2da1c058e2bdf4d2b1d747457047862c5ff4b99c462307abcb9b54f82","abstract_canon_sha256":"76722dff4ed8b881495c7f0e324fd11a9dd8871a758a947e9c099e02e8633458"},"schema_version":"1.0"},"canonical_sha256":"66a5ca0649766763fab0c4543eb995b74a198c5a486740d7ce065688818bacfd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:14.492801Z","signature_b64":"OwBG1JxU1+J6nxOUZW6HxQHN5NfeeSH+9y4esfc2siv/J2wNJuLTOUHROBxr7yacUUBY3vdyY4Y74NwlScODCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66a5ca0649766763fab0c4543eb995b74a198c5a486740d7ce065688818bacfd","last_reissued_at":"2026-07-05T07:11:14.492325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:14.492325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.02169","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7XJ5Edyf0mnDd6Ua/YEvonjnpARHYFxAOEA5JMz/x/BMfS7Vm1DZcGQXNYFt0ZP8Dqnl2ocp2PToaiZM6KrxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:11:25.874242Z"},"content_sha256":"0da3de3a44260aa54cb033a9a1f34357ee5dc82fb4dae075e1841b5551275ef1","schema_version":"1.0","event_id":"sha256:0da3de3a44260aa54cb033a9a1f34357ee5dc82fb4dae075e1841b5551275ef1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:M2S4UBSJOZTWH6VQYRKD5OMVW5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brandon Theodorou, Cao Xiao, Jimeng Sun","submitted_at":"2023-04-04T23:53:34Z","abstract_excerpt":"Synthetic electronic health records (EHRs) that are both realistic and preserve privacy can serve as an alternative to real EHRs for machine learning (ML) modeling and statistical analysis. However, generating high-fidelity and granular electronic health record (EHR) data in its original, highly-dimensional form poses challenges for existing methods due to the complexities inherent in high-dimensional data. In this paper, we propose Hierarchical Autoregressive Language mOdel (HALO) for generating longitudinal high-dimensional EHR, which preserve the statistical properties of real EHR and can b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02169","kind":"arxiv","version":3},"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/2304.02169/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":"2026-07-05T07:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B9aCHmBldcGzWfxcEDPSPqag/xEl1z/MbFaDgVL1IIsIbEol5HCp4/A9Haqlr6G9hBYw4IZraeiWKk+itV5MCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:11:25.874818Z"},"content_sha256":"dcbed8ba74b7d39095ea77bc02d781cf9ac6ce0b36efc81aef48945726889194","schema_version":"1.0","event_id":"sha256:dcbed8ba74b7d39095ea77bc02d781cf9ac6ce0b36efc81aef48945726889194"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2S4UBSJOZTWH6VQYRKD5OMVW5/bundle.json","state_url":"https://pith.science/pith/M2S4UBSJOZTWH6VQYRKD5OMVW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2S4UBSJOZTWH6VQYRKD5OMVW5/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":"2026-08-23T13:11:25Z","links":{"resolver":"https://pith.science/pith/M2S4UBSJOZTWH6VQYRKD5OMVW5","bundle":"https://pith.science/pith/M2S4UBSJOZTWH6VQYRKD5OMVW5/bundle.json","state":"https://pith.science/pith/M2S4UBSJOZTWH6VQYRKD5OMVW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2S4UBSJOZTWH6VQYRKD5OMVW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M2S4UBSJOZTWH6VQYRKD5OMVW5","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":"76722dff4ed8b881495c7f0e324fd11a9dd8871a758a947e9c099e02e8633458","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-04T23:53:34Z","title_canon_sha256":"78038ac2da1c058e2bdf4d2b1d747457047862c5ff4b99c462307abcb9b54f82"},"schema_version":"1.0","source":{"id":"2304.02169","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02169","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02169v3","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02169","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"M2S4UBSJOZTW","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"M2S4UBSJOZTWH6VQ","created_at":"2026-07-05T07:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"M2S4UBSJ","created_at":"2026-07-05T07:11:14Z"}],"graph_snapshots":[{"event_id":"sha256:dcbed8ba74b7d39095ea77bc02d781cf9ac6ce0b36efc81aef48945726889194","target":"graph","created_at":"2026-07-05T07:11:14Z","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/2304.02169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic electronic health records (EHRs) that are both realistic and preserve privacy can serve as an alternative to real EHRs for machine learning (ML) modeling and statistical analysis. However, generating high-fidelity and granular electronic health record (EHR) data in its original, highly-dimensional form poses challenges for existing methods due to the complexities inherent in high-dimensional data. In this paper, we propose Hierarchical Autoregressive Language mOdel (HALO) for generating longitudinal high-dimensional EHR, which preserve the statistical properties of real EHR and can b","authors_text":"Brandon Theodorou, Cao Xiao, Jimeng Sun","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-04T23:53:34Z","title":"Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02169","kind":"arxiv","version":3},"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":"sha256:0da3de3a44260aa54cb033a9a1f34357ee5dc82fb4dae075e1841b5551275ef1","target":"record","created_at":"2026-07-05T07:11:14Z","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":"76722dff4ed8b881495c7f0e324fd11a9dd8871a758a947e9c099e02e8633458","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-04T23:53:34Z","title_canon_sha256":"78038ac2da1c058e2bdf4d2b1d747457047862c5ff4b99c462307abcb9b54f82"},"schema_version":"1.0","source":{"id":"2304.02169","kind":"arxiv","version":3}},"canonical_sha256":"66a5ca0649766763fab0c4543eb995b74a198c5a486740d7ce065688818bacfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66a5ca0649766763fab0c4543eb995b74a198c5a486740d7ce065688818bacfd","first_computed_at":"2026-07-05T07:11:14.492325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:14.492325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OwBG1JxU1+J6nxOUZW6HxQHN5NfeeSH+9y4esfc2siv/J2wNJuLTOUHROBxr7yacUUBY3vdyY4Y74NwlScODCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:14.492801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.02169","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0da3de3a44260aa54cb033a9a1f34357ee5dc82fb4dae075e1841b5551275ef1","sha256:dcbed8ba74b7d39095ea77bc02d781cf9ac6ce0b36efc81aef48945726889194"],"state_sha256":"3d1120e074151326481ca2d282e1ad9346aa61f14450a9d91a8dd94a1afc3049"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hWWBBrQzwkEE1TenghfSKvfXe4IlGDzEESaLbAJSIfBg8nd8Q0P81WPIKDOUuI+ZQIpvMa3nK0R8Nmnhhq9LCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T13:11:25.879527Z","bundle_sha256":"8afe2807aa36ce2c72051f34e401ed5456a4bfaf8162fbb1d49305cbc0286761"}}