{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GZHGIILIS34HCOGFPVENLY5I5F","short_pith_number":"pith:GZHGIILI","schema_version":"1.0","canonical_sha256":"364e64216896f87138c57d48d5e3a8e9462be6fcdbd107fb44386d6947ad2f65","source":{"kind":"arxiv","id":"2411.13428","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.13428","created_at":"2026-07-05T09:38:16.754932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13428v1","created_at":"2026-07-05T09:38:16.754932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13428","created_at":"2026-07-05T09:38:16.754932+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZHGIILIS34H","created_at":"2026-07-05T09:38:16.754932+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZHGIILIS34HCOGF","created_at":"2026-07-05T09:38:16.754932+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZHGIILI","created_at":"2026-07-05T09:38:16.754932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06647","citing_title":"Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGN","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F","json":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F.json","graph_json":"https://pith.science/api/pith-number/GZHGIILIS34HCOGFPVENLY5I5F/graph.json","events_json":"https://pith.science/api/pith-number/GZHGIILIS34HCOGFPVENLY5I5F/events.json","paper":"https://pith.science/paper/GZHGIILI"},"agent_actions":{"view_html":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F","download_json":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F.json","view_paper":"https://pith.science/paper/GZHGIILI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13428&json=true","fetch_graph":"https://pith.science/api/pith-number/GZHGIILIS34HCOGFPVENLY5I5F/graph.json","fetch_events":"https://pith.science/api/pith-number/GZHGIILIS34HCOGFPVENLY5I5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F/action/storage_attestation","attest_author":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F/action/author_attestation","sign_citation":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F/action/citation_signature","submit_replication":"https://pith.science/pith/GZHGIILIS34HCOGFPVENLY5I5F/action/replication_record"}},"created_at":"2026-07-05T09:38:16.754932+00:00","updated_at":"2026-07-05T09:38:16.754932+00:00"}