{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GZHGIILIS34HCOGFPVENLY5I5F","short_pith_number":"pith:GZHGIILI","canonical_record":{"source":{"id":"2411.13428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T16:11:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"393ac67a7a2bf0012267d207d98692a9fda202bd96dad676f73d7266ccbd61b7","abstract_canon_sha256":"e8ffd9a38ac5e7bdbf2f0ca687d538a95fd1dc6b4057701241b6790c2987ecd8"},"schema_version":"1.0"},"canonical_sha256":"364e64216896f87138c57d48d5e3a8e9462be6fcdbd107fb44386d6947ad2f65","source":{"kind":"arxiv","id":"2411.13428","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13428","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13428v1","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13428","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_12","alias_value":"GZHGIILIS34H","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_16","alias_value":"GZHGIILIS34HCOGF","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_8","alias_value":"GZHGIILI","created_at":"2026-07-05T09:38:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GZHGIILIS34HCOGFPVENLY5I5F","target":"record","payload":{"canonical_record":{"source":{"id":"2411.13428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T16:11:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"393ac67a7a2bf0012267d207d98692a9fda202bd96dad676f73d7266ccbd61b7","abstract_canon_sha256":"e8ffd9a38ac5e7bdbf2f0ca687d538a95fd1dc6b4057701241b6790c2987ecd8"},"schema_version":"1.0"},"canonical_sha256":"364e64216896f87138c57d48d5e3a8e9462be6fcdbd107fb44386d6947ad2f65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:16.755426Z","signature_b64":"mwW6lFb4zu+z0KuZgCBOqj3t2tOMOSXQCwrAZKs81tveV+q25QfAey8JvP3XlSnhZiPSazNiYmqb6yh8J401AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"364e64216896f87138c57d48d5e3a8e9462be6fcdbd107fb44386d6947ad2f65","last_reissued_at":"2026-07-05T09:38:16.754874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:16.754874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.13428","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":"2026-07-05T09:38:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yfzvGj760NXzg/WsjNWOWQHy6Ergv2UAzeppgHTV2IXLrUUmA9r8+0Pk97DAW5NoXNgiupgs6t7LrBmGJsufCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:40:25.188982Z"},"content_sha256":"11ec4898bc66a8496587d0dc34a5f89059d5789406a328337ff77ae6ef455231","schema_version":"1.0","event_id":"sha256:11ec4898bc66a8496587d0dc34a5f89059d5789406a328337ff77ae6ef455231"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GZHGIILIS34HCOGFPVENLY5I5F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SynEHRgy: Synthesizing Mixed-Type Structured Electronic Health Records using Decoder-Only Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anisoara Ionescu, David Atienza, Hojjat Karami","submitted_at":"2024-11-20T16:11:20Z","abstract_excerpt":"Generating synthetic Electronic Health Records (EHRs) offers significant potential for data augmentation, privacy-preserving data sharing, and improving machine learning model training. We propose a novel tokenization strategy tailored for structured EHR data, which encompasses diverse data types such as covariates, ICD codes, and irregularly sampled time series. Using a GPT-like decoder-only transformer model, we demonstrate the generation of high-quality synthetic EHRs. Our approach is evaluated using the MIMIC-III dataset, and we benchmark the fidelity, utility, and privacy of the generated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13428","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/2411.13428/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":"2026-07-05T09:38:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3GpZBCpkt/EUHG6Bti/VSDCQZcbNxSOg0rKvZ8coWuj98I41i240tpKOqiPkttj6mOM0Rw+TNOpREBh865ldAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:40:25.189534Z"},"content_sha256":"dddaca4199b3191e67b1a33840fa738f1968e384f95abea692f2392fcb330b71","schema_version":"1.0","event_id":"sha256:dddaca4199b3191e67b1a33840fa738f1968e384f95abea692f2392fcb330b71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F/bundle.json","state_url":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZHGIILIS34HCOGFPVENLY5I5F/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":"2026-08-07T15:40:25Z","links":{"resolver":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F","bundle":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F/bundle.json","state":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZHGIILIS34HCOGFPVENLY5I5F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GZHGIILIS34HCOGFPVENLY5I5F","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":"e8ffd9a38ac5e7bdbf2f0ca687d538a95fd1dc6b4057701241b6790c2987ecd8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T16:11:20Z","title_canon_sha256":"393ac67a7a2bf0012267d207d98692a9fda202bd96dad676f73d7266ccbd61b7"},"schema_version":"1.0","source":{"id":"2411.13428","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13428","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13428v1","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13428","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_12","alias_value":"GZHGIILIS34H","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_16","alias_value":"GZHGIILIS34HCOGF","created_at":"2026-07-05T09:38:16Z"},{"alias_kind":"pith_short_8","alias_value":"GZHGIILI","created_at":"2026-07-05T09:38:16Z"}],"graph_snapshots":[{"event_id":"sha256:dddaca4199b3191e67b1a33840fa738f1968e384f95abea692f2392fcb330b71","target":"graph","created_at":"2026-07-05T09:38:16Z","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/2411.13428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating synthetic Electronic Health Records (EHRs) offers significant potential for data augmentation, privacy-preserving data sharing, and improving machine learning model training. We propose a novel tokenization strategy tailored for structured EHR data, which encompasses diverse data types such as covariates, ICD codes, and irregularly sampled time series. Using a GPT-like decoder-only transformer model, we demonstrate the generation of high-quality synthetic EHRs. Our approach is evaluated using the MIMIC-III dataset, and we benchmark the fidelity, utility, and privacy of the generated","authors_text":"Anisoara Ionescu, David Atienza, Hojjat Karami","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T16:11:20Z","title":"SynEHRgy: Synthesizing Mixed-Type Structured Electronic Health Records using Decoder-Only Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13428","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":"sha256:11ec4898bc66a8496587d0dc34a5f89059d5789406a328337ff77ae6ef455231","target":"record","created_at":"2026-07-05T09:38:16Z","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":"e8ffd9a38ac5e7bdbf2f0ca687d538a95fd1dc6b4057701241b6790c2987ecd8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T16:11:20Z","title_canon_sha256":"393ac67a7a2bf0012267d207d98692a9fda202bd96dad676f73d7266ccbd61b7"},"schema_version":"1.0","source":{"id":"2411.13428","kind":"arxiv","version":1}},"canonical_sha256":"364e64216896f87138c57d48d5e3a8e9462be6fcdbd107fb44386d6947ad2f65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"364e64216896f87138c57d48d5e3a8e9462be6fcdbd107fb44386d6947ad2f65","first_computed_at":"2026-07-05T09:38:16.754874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:16.754874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mwW6lFb4zu+z0KuZgCBOqj3t2tOMOSXQCwrAZKs81tveV+q25QfAey8JvP3XlSnhZiPSazNiYmqb6yh8J401AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:16.755426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13428","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ec4898bc66a8496587d0dc34a5f89059d5789406a328337ff77ae6ef455231","sha256:dddaca4199b3191e67b1a33840fa738f1968e384f95abea692f2392fcb330b71"],"state_sha256":"ef281451ec70a7f30af226b18330939a7d4b60a7a5da41ec5f79f566cccfe26d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2QO/VjtDZooIhbmKAFVLRmz3ET2XNx4STEdYF3vYzO0MjwJr1ew43QRpbaoWGqADVkRSyIF2ZhuBB7b3IMwAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:40:25.193991Z","bundle_sha256":"0a4ee2ff8693e2f80bffb4a880ffa7f0a87f1164267b084ef7098ad2875e9550"}}