{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MB5SDETMHGITZALBLRPWAJJC4E","short_pith_number":"pith:MB5SDETM","canonical_record":{"source":{"id":"2201.05400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-14T11:35:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e828374fc37ff3b2f9e874fd95da1403a8477246967226c690d9a548555f69fa","abstract_canon_sha256":"96549bbeb846251ef542ed92dd820e873d1f9b2a4e9578c5a1abee4574837dd2"},"schema_version":"1.0"},"canonical_sha256":"607b21926c39913c81615c5f602522e12c1bc80dbff047c398e8f8f5687acac7","source":{"kind":"arxiv","id":"2201.05400","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05400","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05400v1","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05400","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"MB5SDETMHGIT","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"MB5SDETMHGITZALB","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"MB5SDETM","created_at":"2026-07-05T03:48:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MB5SDETMHGITZALBLRPWAJJC4E","target":"record","payload":{"canonical_record":{"source":{"id":"2201.05400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-14T11:35:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e828374fc37ff3b2f9e874fd95da1403a8477246967226c690d9a548555f69fa","abstract_canon_sha256":"96549bbeb846251ef542ed92dd820e873d1f9b2a4e9578c5a1abee4574837dd2"},"schema_version":"1.0"},"canonical_sha256":"607b21926c39913c81615c5f602522e12c1bc80dbff047c398e8f8f5687acac7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:32.055694Z","signature_b64":"70IF7XEvaqHRb8VK5AStMUYHDdL4XX6uHPYVguz7Ge0q6D1Jw7nbLsiBcdCYFKv0eh299+pLUhi4S8aueyghAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"607b21926c39913c81615c5f602522e12c1bc80dbff047c398e8f8f5687acac7","last_reissued_at":"2026-07-05T03:48:32.055320Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:32.055320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.05400","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":"2026-07-05T03:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fr8T4SgHAQ5BqlUtjIQBQ+4SkRqUjpGjrAShZVq8SG9bCb3NOk7jtcOe6i3ePMCCML6yVrup964FBAZqWWOuAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T17:34:09.407468Z"},"content_sha256":"9c4db63daccfb9fb8e79aef3163ce08b06ef5233161af361ef03706f47d07980","schema_version":"1.0","event_id":"sha256:9c4db63daccfb9fb8e79aef3163ce08b06ef5233161af361ef03706f47d07980"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MB5SDETMHGITZALBLRPWAJJC4E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthesising Electronic Health Records: Cystic Fibrosis Patient Group","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emily Muller, Jer Hayes, Xu Zheng","submitted_at":"2022-01-14T11:35:18Z","abstract_excerpt":"Class imbalance can often degrade predictive performance of supervised learning algorithms. Balanced classes can be obtained by oversampling exact copies, with noise, or interpolation between nearest neighbours (as in traditional SMOTE methods). Oversampling tabular data using augmentation, as is typical in computer vision tasks, can be achieved with deep generative models. Deep generative models are effective data synthesisers due to their ability to capture complex underlying distributions. Synthetic data in healthcare can enhance interoperability between healthcare providers by ensuring pat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05400","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/2201.05400/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6L9IFIBZ9eZCuW02qHoc4X1yCXnOxz/S1T8G6+5EYb6gtSthdvFpe1tbc2bUGdCBx0suJFEekmCcR/SjS9SyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T17:34:09.407829Z"},"content_sha256":"53eaac22cfc6d785890fd75a61d4af0c45e61e446c728c218de8322412435de2","schema_version":"1.0","event_id":"sha256:53eaac22cfc6d785890fd75a61d4af0c45e61e446c728c218de8322412435de2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MB5SDETMHGITZALBLRPWAJJC4E/bundle.json","state_url":"https://pith.science/pith/MB5SDETMHGITZALBLRPWAJJC4E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MB5SDETMHGITZALBLRPWAJJC4E/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":"2026-07-13T17:34:09Z","links":{"resolver":"https://pith.science/pith/MB5SDETMHGITZALBLRPWAJJC4E","bundle":"https://pith.science/pith/MB5SDETMHGITZALBLRPWAJJC4E/bundle.json","state":"https://pith.science/pith/MB5SDETMHGITZALBLRPWAJJC4E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MB5SDETMHGITZALBLRPWAJJC4E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MB5SDETMHGITZALBLRPWAJJC4E","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":"96549bbeb846251ef542ed92dd820e873d1f9b2a4e9578c5a1abee4574837dd2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-14T11:35:18Z","title_canon_sha256":"e828374fc37ff3b2f9e874fd95da1403a8477246967226c690d9a548555f69fa"},"schema_version":"1.0","source":{"id":"2201.05400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05400","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05400v1","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05400","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"MB5SDETMHGIT","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"MB5SDETMHGITZALB","created_at":"2026-07-05T03:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"MB5SDETM","created_at":"2026-07-05T03:48:32Z"}],"graph_snapshots":[{"event_id":"sha256:53eaac22cfc6d785890fd75a61d4af0c45e61e446c728c218de8322412435de2","target":"graph","created_at":"2026-07-05T03:48:32Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.05400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Class imbalance can often degrade predictive performance of supervised learning algorithms. Balanced classes can be obtained by oversampling exact copies, with noise, or interpolation between nearest neighbours (as in traditional SMOTE methods). Oversampling tabular data using augmentation, as is typical in computer vision tasks, can be achieved with deep generative models. Deep generative models are effective data synthesisers due to their ability to capture complex underlying distributions. Synthetic data in healthcare can enhance interoperability between healthcare providers by ensuring pat","authors_text":"Emily Muller, Jer Hayes, Xu Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-14T11:35:18Z","title":"Synthesising Electronic Health Records: Cystic Fibrosis Patient Group"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05400","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":"sha256:9c4db63daccfb9fb8e79aef3163ce08b06ef5233161af361ef03706f47d07980","target":"record","created_at":"2026-07-05T03:48:32Z","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":"96549bbeb846251ef542ed92dd820e873d1f9b2a4e9578c5a1abee4574837dd2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-14T11:35:18Z","title_canon_sha256":"e828374fc37ff3b2f9e874fd95da1403a8477246967226c690d9a548555f69fa"},"schema_version":"1.0","source":{"id":"2201.05400","kind":"arxiv","version":1}},"canonical_sha256":"607b21926c39913c81615c5f602522e12c1bc80dbff047c398e8f8f5687acac7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"607b21926c39913c81615c5f602522e12c1bc80dbff047c398e8f8f5687acac7","first_computed_at":"2026-07-05T03:48:32.055320Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:48:32.055320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"70IF7XEvaqHRb8VK5AStMUYHDdL4XX6uHPYVguz7Ge0q6D1Jw7nbLsiBcdCYFKv0eh299+pLUhi4S8aueyghAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:48:32.055694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.05400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c4db63daccfb9fb8e79aef3163ce08b06ef5233161af361ef03706f47d07980","sha256:53eaac22cfc6d785890fd75a61d4af0c45e61e446c728c218de8322412435de2"],"state_sha256":"f2de0051969c8d4b5e8718af78b9247d0ac9b49aa7491fa5307ede1bc5176654"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6bU3XWw6qC5PI56qAkYkr7xSmgw3NlVV9nBf1wHMdQ+Ll6y5nNrc9NU9Pr/6GN0Lv9mP7GPmCqzAI6w0fhiIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T17:34:09.410135Z","bundle_sha256":"cad664535d7b8eecf3be2a8533a151016c882d3fd08d9a3ae2f9cfa1a57c9386"}}