{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RETVFJYW62V5NPEAOL5BIPERAM","short_pith_number":"pith:RETVFJYW","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"},"canonical_sha256":"892752a716f6abd6bc8072fa143c9103370af39aa2c339e0affe479ee52cf74e","source":{"kind":"arxiv","id":"1807.01514","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01514","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01514v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01514","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"RETVFJYW62V5","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RETVFJYW62V5NPEA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RETVFJYW","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RETVFJYW62V5NPEAOL5BIPERAM","target":"record","payload":{"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"},"canonical_sha256":"892752a716f6abd6bc8072fa143c9103370af39aa2c339e0affe479ee52cf74e","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"},"source_kind":"arxiv","source_id":"1807.01514","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zrrfypvn4rRPllDa2rBFfeb365FJ2kLOFjvJP6d/C7zBqCwazqy4Aw6omvZwcK2xihTxqW/av80nMp8AckkjAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:48:42.280349Z"},"content_sha256":"b6a1184f25445766eeb520e85643087f6a4f2670e1917032b89090a352c396dd","schema_version":"1.0","event_id":"sha256:b6a1184f25445766eeb520e85643087f6a4f2670e1917032b89090a352c396dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RETVFJYW62V5NPEAOL5BIPERAM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6WWo2EKugmWb9bMDu9nNT5jQ7d1RDaACsICCo14DzWPWk3Xatm27sopGon4lsV0S7wJYUvt+R2tLE9PooY5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:48:42.280839Z"},"content_sha256":"b955d8f4a9be93c65fce17ca8112c9ed62c40fc328e1661e8232a945dcba9c03","schema_version":"1.0","event_id":"sha256:b955d8f4a9be93c65fce17ca8112c9ed62c40fc328e1661e8232a945dcba9c03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM/bundle.json","state_url":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RETVFJYW62V5NPEAOL5BIPERAM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T15:48:42Z","links":{"resolver":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM","bundle":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM/bundle.json","state":"https://pith.science/pith/RETVFJYW62V5NPEAOL5BIPERAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RETVFJYW62V5NPEAOL5BIPERAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RETVFJYW62V5NPEAOL5BIPERAM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6b9dd159e0a6d392cce717f6c9100ce449b89c89152b9f52e67c09452984d2af","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-04T10:55:38Z","title_canon_sha256":"61e8ce5a247f76d7f73f7b42cc847072492ac77748a578708f1bccc10cbbe03b"},"schema_version":"1.0","source":{"id":"1807.01514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01514","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01514v1","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01514","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"RETVFJYW62V5","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RETVFJYW62V5NPEA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RETVFJYW","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:b955d8f4a9be93c65fce17ca8112c9ed62c40fc328e1661e8232a945dcba9c03","target":"graph","created_at":"2026-05-18T00:11:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Laura Avi\\~n\\'o, Matteo Ruffini, Ricard Gavald\\`a","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-04T10:55:38Z","title":"Generating Synthetic but Plausible Healthcare Record Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01514","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b6a1184f25445766eeb520e85643087f6a4f2670e1917032b89090a352c396dd","target":"record","created_at":"2026-05-18T00:11:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6b9dd159e0a6d392cce717f6c9100ce449b89c89152b9f52e67c09452984d2af","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-04T10:55:38Z","title_canon_sha256":"61e8ce5a247f76d7f73f7b42cc847072492ac77748a578708f1bccc10cbbe03b"},"schema_version":"1.0","source":{"id":"1807.01514","kind":"arxiv","version":1}},"canonical_sha256":"892752a716f6abd6bc8072fa143c9103370af39aa2c339e0affe479ee52cf74e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"892752a716f6abd6bc8072fa143c9103370af39aa2c339e0affe479ee52cf74e","first_computed_at":"2026-05-18T00:11:29.560574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:29.560574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0aNRREnBcRvf4JoZks3mO+9RHuspr5iNWm1otCYzOUb8LoIvCvKc6N8gemwZkHSEGGHlKtOqmYwXBPFslLhFCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:29.561020Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6a1184f25445766eeb520e85643087f6a4f2670e1917032b89090a352c396dd","sha256:b955d8f4a9be93c65fce17ca8112c9ed62c40fc328e1661e8232a945dcba9c03"],"state_sha256":"65e64e55dd50665121154e12bd54594fd42a97942fc5cda6f70c4d8e91a36516"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1L697AnT3iHNKPbl4QiKRKKAL3Ie39+w/25fZuDJmzASVjVGlMEbMgGsl8q3oDYD+bAfEKrfFSVQinvxzJajAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:48:42.289783Z","bundle_sha256":"e3c44b8c7360f242de4afcaae3671f37368a3df972abc1b4849f2d1996937620"}}