{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZXZ4WRWEJZRWD46SZTCFWQ2WPU","short_pith_number":"pith:ZXZ4WRWE","schema_version":"1.0","canonical_sha256":"cdf3cb46c44e6361f3d2ccc45b43567d28ea432d5414cd4113e071c549fd50ad","source":{"kind":"arxiv","id":"2303.12281","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Health-related Longitudinal Data with Mixed-type Variables Generated using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Louisa Jorm, Nicholas I-Hsien Kuo, Sebastiano Barbieri","submitted_at":"2023-03-22T03:15:33Z","abstract_excerpt":"This paper presents a novel approach to simulating electronic health records (EHRs) using diffusion probabilistic models (DPMs). Specifically, we demonstrate the effectiveness of DPMs in synthesising longitudinal EHRs that capture mixed-type variables, including numeric, binary, and categorical variables. To our knowledge, this represents the first use of DPMs for this purpose. We compared our DPM-simulated datasets to previous state-of-the-art results based on generative adversarial networks (GANs) for two clinical applications: acute hypotension and human immunodeficiency virus (ART for HIV)"},"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":"2303.12281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-22T03:15:33Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"9b8eeb29a3c6a5114a25b0d4594e0d57cdff74afb7d7f7b7111d30b421cd4b85","abstract_canon_sha256":"ed658967c3df590576c69419334e72d260dd9e6b57864789b125e0034d2247a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:39.288274Z","signature_b64":"aeC67te8WfjygGdFZoxspmPjEOPNgowIppMv1WJXUfT174bQ5Ebt+SkO0RLEUSlPU0DKsySotTCxALQqUBdeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdf3cb46c44e6361f3d2ccc45b43567d28ea432d5414cd4113e071c549fd50ad","last_reissued_at":"2026-07-05T05:53:39.287937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:39.287937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Health-related Longitudinal Data with Mixed-type Variables Generated using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Louisa Jorm, Nicholas I-Hsien Kuo, Sebastiano Barbieri","submitted_at":"2023-03-22T03:15:33Z","abstract_excerpt":"This paper presents a novel approach to simulating electronic health records (EHRs) using diffusion probabilistic models (DPMs). Specifically, we demonstrate the effectiveness of DPMs in synthesising longitudinal EHRs that capture mixed-type variables, including numeric, binary, and categorical variables. To our knowledge, this represents the first use of DPMs for this purpose. We compared our DPM-simulated datasets to previous state-of-the-art results based on generative adversarial networks (GANs) for two clinical applications: acute hypotension and human immunodeficiency virus (ART for HIV)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12281","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/2303.12281/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":"2303.12281","created_at":"2026-07-05T05:53:39.287993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12281v1","created_at":"2026-07-05T05:53:39.287993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12281","created_at":"2026-07-05T05:53:39.287993+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXZ4WRWEJZRW","created_at":"2026-07-05T05:53:39.287993+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXZ4WRWEJZRWD46S","created_at":"2026-07-05T05:53:39.287993+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXZ4WRWE","created_at":"2026-07-05T05:53:39.287993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25762","citing_title":"OncoSynth: Synthetic data generation for treatment effect estimation in oncology","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXZ4WRWEJZRWD46SZTCFWQ2WPU","json":"https://pith.science/pith/ZXZ4WRWEJZRWD46SZTCFWQ2WPU.json","graph_json":"https://pith.science/api/pith-number/ZXZ4WRWEJZRWD46SZTCFWQ2WPU/graph.json","events_json":"https://pith.science/api/pith-number/ZXZ4WRWEJZRWD46SZTCFWQ2WPU/events.json","paper":"https://pith.science/paper/ZXZ4WRWE"},"agent_actions":{"view_html":"https://pith.science/pith/ZXZ4WRWEJZRWD46SZTCFWQ2WPU","download_json":"https://pith.science/pith/ZXZ4WRWEJZRWD46SZTCFWQ2WPU.json","view_paper":"https://pith.science/paper/ZXZ4WRWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12281&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXZ4WRWEJZRWD46SZTCFWQ2WPU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXZ4WRWEJZRWD46SZTCFWQ2WPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXZ4WRWEJZRWD46SZTCFWQ2WPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXZ4WRWEJZRWD46SZTCFWQ2WPU/action/storage_attestation","attest_author":"https://pith.science/pith/ZXZ4WRWEJZRWD46SZTCFWQ2WPU/action/author_attestation","sign_citation":"https://pith.science/pith/ZXZ4WRWEJZRWD46SZTCFWQ2WPU/action/citation_signature","submit_replication":"https://pith.science/pith/ZXZ4WRWEJZRWD46SZTCFWQ2WPU/action/replication_record"}},"created_at":"2026-07-05T05:53:39.287993+00:00","updated_at":"2026-07-05T05:53:39.287993+00:00"}