{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RETVFJYW62V5NPEAOL5BIPERAM","short_pith_number":"pith:RETVFJYW","schema_version":"1.0","canonical_sha256":"892752a716f6abd6bc8072fa143c9103370af39aa2c339e0affe479ee52cf74e","source":{"kind":"arxiv","id":"1807.01514","version":1},"attestation_state":"computed","paper":{"title":"Generating Synthetic but Plausible Healthcare Record Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Laura Avi\\~n\\'o, Matteo Ruffini, Ricard Gavald\\`a","submitted_at":"2018-07-04T10:55:38Z","abstract_excerpt":"Generating datasets that \"look like\" given real ones is an interesting tasks for healthcare applications of ML and many other fields of science and engineering. In this paper we propose a new method of general application to binary datasets based on a method for learning the parameters of a latent variable moment that we have previously used for clustering patient datasets. We compare our method with a recent proposal (MedGan) based on generative adversarial methods and find that the synthetic datasets we generate are globally more realistic in at least two senses: real and synthetic instances"},"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":"1807.01514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-04T10:55:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"61e8ce5a247f76d7f73f7b42cc847072492ac77748a578708f1bccc10cbbe03b","abstract_canon_sha256":"6b9dd159e0a6d392cce717f6c9100ce449b89c89152b9f52e67c09452984d2af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:29.561020Z","signature_b64":"0aNRREnBcRvf4JoZks3mO+9RHuspr5iNWm1otCYzOUb8LoIvCvKc6N8gemwZkHSEGGHlKtOqmYwXBPFslLhFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"892752a716f6abd6bc8072fa143c9103370af39aa2c339e0affe479ee52cf74e","last_reissued_at":"2026-05-18T00:11:29.560574Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:29.560574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Synthetic but Plausible Healthcare Record Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Laura Avi\\~n\\'o, Matteo Ruffini, Ricard Gavald\\`a","submitted_at":"2018-07-04T10:55:38Z","abstract_excerpt":"Generating datasets that \"look like\" given real ones is an interesting tasks for healthcare applications of ML and many other fields of science and engineering. In this paper we propose a new method of general application to binary datasets based on a method for learning the parameters of a latent variable moment that we have previously used for clustering patient datasets. We compare our method with a recent proposal (MedGan) based on generative adversarial methods and find that the synthetic datasets we generate are globally more realistic in at least two senses: real and synthetic instances"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01514","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":""},"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":"1807.01514","created_at":"2026-05-18T00:11:29.560640+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.01514v1","created_at":"2026-05-18T00:11:29.560640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01514","created_at":"2026-05-18T00:11:29.560640+00:00"},{"alias_kind":"pith_short_12","alias_value":"RETVFJYW62V5","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RETVFJYW62V5NPEA","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RETVFJYW","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21330","citing_title":"Stage-Diff: Stage-wise Long-Term Time Series Generation Based on Diffusion Models","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM","json":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM.json","graph_json":"https://pith.science/api/pith-number/RETVFJYW62V5NPEAOL5BIPERAM/graph.json","events_json":"https://pith.science/api/pith-number/RETVFJYW62V5NPEAOL5BIPERAM/events.json","paper":"https://pith.science/paper/RETVFJYW"},"agent_actions":{"view_html":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM","download_json":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM.json","view_paper":"https://pith.science/paper/RETVFJYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.01514&json=true","fetch_graph":"https://pith.science/api/pith-number/RETVFJYW62V5NPEAOL5BIPERAM/graph.json","fetch_events":"https://pith.science/api/pith-number/RETVFJYW62V5NPEAOL5BIPERAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM/action/storage_attestation","attest_author":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM/action/author_attestation","sign_citation":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM/action/citation_signature","submit_replication":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM/action/replication_record"}},"created_at":"2026-05-18T00:11:29.560640+00:00","updated_at":"2026-05-18T00:11:29.560640+00:00"}