{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NHCMVOUOTSRG4P7GGKIH6VW4C5","short_pith_number":"pith:NHCMVOUO","schema_version":"1.0","canonical_sha256":"69c4caba8e9ca26e3fe632907f56dc1761085c38982344182f5a5709a2ec3b59","source":{"kind":"arxiv","id":"2302.04355","version":1},"attestation_state":"computed","paper":{"title":"MedDiff: Generating Electronic Health Records using Accelerated Denoising Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Huan He, Joyce C Ho, Shifan Zhao, Yuanzhe Xi","submitted_at":"2023-02-08T22:06:34Z","abstract_excerpt":"Due to patient privacy protection concerns, machine learning research in healthcare has been undeniably slower and limited than in other application domains. High-quality, realistic, synthetic electronic health records (EHRs) can be leveraged to accelerate methodological developments for research purposes while mitigating privacy concerns associated with data sharing. The current state-of-the-art model for synthetic EHR generation is generative adversarial networks, which are notoriously difficult to train and can suffer from mode collapse. Denoising Diffusion Probabilistic Models, a class of "},"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":"2302.04355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T22:06:34Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"26b07845c6405bb129e0fc3e325e6fb0c7709bfecdce8710ab7b101842bcaf7d","abstract_canon_sha256":"b6b24bfd2cd865ead6e0d722a169cabcc54ceec10680262e4b9e45549bc21339"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:12.794474Z","signature_b64":"EJJqW7U6CpxGXwq6WHPw4SnLizcFWjrOSVp1lnEQbTj478i0Pls9P9riRBEZxu8459cFmKQbFLZT0Ipj4yRYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c4caba8e9ca26e3fe632907f56dc1761085c38982344182f5a5709a2ec3b59","last_reissued_at":"2026-07-05T05:40:12.794018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:12.794018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedDiff: Generating Electronic Health Records using Accelerated Denoising Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Huan He, Joyce C Ho, Shifan Zhao, Yuanzhe Xi","submitted_at":"2023-02-08T22:06:34Z","abstract_excerpt":"Due to patient privacy protection concerns, machine learning research in healthcare has been undeniably slower and limited than in other application domains. High-quality, realistic, synthetic electronic health records (EHRs) can be leveraged to accelerate methodological developments for research purposes while mitigating privacy concerns associated with data sharing. The current state-of-the-art model for synthetic EHR generation is generative adversarial networks, which are notoriously difficult to train and can suffer from mode collapse. Denoising Diffusion Probabilistic Models, a class of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04355","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/2302.04355/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":"2302.04355","created_at":"2026-07-05T05:40:12.794072+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04355v1","created_at":"2026-07-05T05:40:12.794072+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04355","created_at":"2026-07-05T05:40:12.794072+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHCMVOUOTSRG","created_at":"2026-07-05T05:40:12.794072+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHCMVOUOTSRG4P7G","created_at":"2026-07-05T05:40:12.794072+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHCMVOUO","created_at":"2026-07-05T05:40:12.794072+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25762","citing_title":"OncoSynth: Synthetic data generation for treatment effect estimation in oncology","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17119","citing_title":"Diffusion and Flow Matching Models for Tabular Data: A Survey","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14422","citing_title":"What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHCMVOUOTSRG4P7GGKIH6VW4C5","json":"https://pith.science/pith/NHCMVOUOTSRG4P7GGKIH6VW4C5.json","graph_json":"https://pith.science/api/pith-number/NHCMVOUOTSRG4P7GGKIH6VW4C5/graph.json","events_json":"https://pith.science/api/pith-number/NHCMVOUOTSRG4P7GGKIH6VW4C5/events.json","paper":"https://pith.science/paper/NHCMVOUO"},"agent_actions":{"view_html":"https://pith.science/pith/NHCMVOUOTSRG4P7GGKIH6VW4C5","download_json":"https://pith.science/pith/NHCMVOUOTSRG4P7GGKIH6VW4C5.json","view_paper":"https://pith.science/paper/NHCMVOUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04355&json=true","fetch_graph":"https://pith.science/api/pith-number/NHCMVOUOTSRG4P7GGKIH6VW4C5/graph.json","fetch_events":"https://pith.science/api/pith-number/NHCMVOUOTSRG4P7GGKIH6VW4C5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHCMVOUOTSRG4P7GGKIH6VW4C5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHCMVOUOTSRG4P7GGKIH6VW4C5/action/storage_attestation","attest_author":"https://pith.science/pith/NHCMVOUOTSRG4P7GGKIH6VW4C5/action/author_attestation","sign_citation":"https://pith.science/pith/NHCMVOUOTSRG4P7GGKIH6VW4C5/action/citation_signature","submit_replication":"https://pith.science/pith/NHCMVOUOTSRG4P7GGKIH6VW4C5/action/replication_record"}},"created_at":"2026-07-05T05:40:12.794072+00:00","updated_at":"2026-07-05T05:40:12.794072+00:00"}