{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7CZEX54WZVLWBAQII5DF5N2ORT","short_pith_number":"pith:7CZEX54W","schema_version":"1.0","canonical_sha256":"f8b24bf796cd5760820847465eb74e8cf7ea038edfb5f1c1abca2e93bcc92a3e","source":{"kind":"arxiv","id":"2109.02543","version":1},"attestation_state":"computed","paper":{"title":"Generation of Synthetic Electronic Health Records Using a Federated GAN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eoin Brophy, John Weldon, Tomas Ward","submitted_at":"2021-09-06T15:29:15Z","abstract_excerpt":"Sensitive medical data is often subject to strict usage constraints. In this paper, we trained a generative adversarial network (GAN) on real-world electronic health records (EHR). It was then used to create a data-set of \"fake\" patients through synthetic data generation (SDG) to circumvent usage constraints. This real-world data was tabular, binary, intensive care unit (ICU) patient diagnosis data. The entire data-set was split into separate data silos to mimic real-world scenarios where multiple ICU units across different hospitals may have similarly structured data-sets within their own org"},"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":"2109.02543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-06T15:29:15Z","cross_cats_sorted":[],"title_canon_sha256":"9c5743f871bb6da9515e7c59f3c56923c1565b7b335cf2aee62c158526ef3570","abstract_canon_sha256":"7481a9c14015cebd538e09f77a452266fbd134d4c112bc6ec15014e8a37bd6ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:43.563437Z","signature_b64":"9ijWGP4yyBDuU/zn8o9bsCRm2EEgR9mnrOnvSVN+gAlsnYoQOLgLpWye7FwXA6SuJP7FxrZZVtB2Ic1aOXrDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8b24bf796cd5760820847465eb74e8cf7ea038edfb5f1c1abca2e93bcc92a3e","last_reissued_at":"2026-07-05T03:11:43.562976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:43.562976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generation of Synthetic Electronic Health Records Using a Federated GAN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eoin Brophy, John Weldon, Tomas Ward","submitted_at":"2021-09-06T15:29:15Z","abstract_excerpt":"Sensitive medical data is often subject to strict usage constraints. In this paper, we trained a generative adversarial network (GAN) on real-world electronic health records (EHR). It was then used to create a data-set of \"fake\" patients through synthetic data generation (SDG) to circumvent usage constraints. This real-world data was tabular, binary, intensive care unit (ICU) patient diagnosis data. The entire data-set was split into separate data silos to mimic real-world scenarios where multiple ICU units across different hospitals may have similarly structured data-sets within their own org"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02543","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/2109.02543/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":"2109.02543","created_at":"2026-07-05T03:11:43.563032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02543v1","created_at":"2026-07-05T03:11:43.563032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02543","created_at":"2026-07-05T03:11:43.563032+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CZEX54WZVLW","created_at":"2026-07-05T03:11:43.563032+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CZEX54WZVLWBAQI","created_at":"2026-07-05T03:11:43.563032+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CZEX54W","created_at":"2026-07-05T03:11:43.563032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23358","citing_title":"Federated Timeline Synthesis: Scalable and Private Methodology For Model Training and Deployment","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CZEX54WZVLWBAQII5DF5N2ORT","json":"https://pith.science/pith/7CZEX54WZVLWBAQII5DF5N2ORT.json","graph_json":"https://pith.science/api/pith-number/7CZEX54WZVLWBAQII5DF5N2ORT/graph.json","events_json":"https://pith.science/api/pith-number/7CZEX54WZVLWBAQII5DF5N2ORT/events.json","paper":"https://pith.science/paper/7CZEX54W"},"agent_actions":{"view_html":"https://pith.science/pith/7CZEX54WZVLWBAQII5DF5N2ORT","download_json":"https://pith.science/pith/7CZEX54WZVLWBAQII5DF5N2ORT.json","view_paper":"https://pith.science/paper/7CZEX54W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02543&json=true","fetch_graph":"https://pith.science/api/pith-number/7CZEX54WZVLWBAQII5DF5N2ORT/graph.json","fetch_events":"https://pith.science/api/pith-number/7CZEX54WZVLWBAQII5DF5N2ORT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CZEX54WZVLWBAQII5DF5N2ORT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CZEX54WZVLWBAQII5DF5N2ORT/action/storage_attestation","attest_author":"https://pith.science/pith/7CZEX54WZVLWBAQII5DF5N2ORT/action/author_attestation","sign_citation":"https://pith.science/pith/7CZEX54WZVLWBAQII5DF5N2ORT/action/citation_signature","submit_replication":"https://pith.science/pith/7CZEX54WZVLWBAQII5DF5N2ORT/action/replication_record"}},"created_at":"2026-07-05T03:11:43.563032+00:00","updated_at":"2026-07-05T03:11:43.563032+00:00"}