{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YHHKER3ZFMRQ4LIGMMWZFKDCOM","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":"bfc6350adac978400f7fd3b3912907608c02e6dfc9c4f93eb96c41447a06e594","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-31T10:56:20Z","title_canon_sha256":"5b78c399df119e03b73f77bbeea374359ad4c00f4b3fc814918c0698a2f22957"},"schema_version":"1.0","source":{"id":"2407.21523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21523","created_at":"2026-07-05T08:50:40Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21523v1","created_at":"2026-07-05T08:50:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21523","created_at":"2026-07-05T08:50:40Z"},{"alias_kind":"pith_short_12","alias_value":"YHHKER3ZFMRQ","created_at":"2026-07-05T08:50:40Z"},{"alias_kind":"pith_short_16","alias_value":"YHHKER3ZFMRQ4LIG","created_at":"2026-07-05T08:50:40Z"},{"alias_kind":"pith_short_8","alias_value":"YHHKER3Z","created_at":"2026-07-05T08:50:40Z"}],"graph_snapshots":[{"event_id":"sha256:6f65e25a84775f00c292d802e2c158ba7297fbad3279164a327d5017a23ac289","target":"graph","created_at":"2026-07-05T08:50:40Z","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/2407.21523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning (ML) on tabular data is ubiquitous, yet obtaining abundant high-quality tabular data for model training remains a significant obstacle. Numerous works have focused on tabular data augmentation (TDA) to enhance the original table with additional data, thereby improving downstream ML tasks. Recently, there has been a growing interest in leveraging the capabilities of generative AI for TDA. Therefore, we believe it is time to provide a comprehensive review of the progress and future prospects of TDA, with a particular emphasis on the trending generative AI. Specifically, we prese","authors_text":"Gang Chen, Huan Li, Ke Chen, Lidan Shou, Lingxi Cui","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-31T10:56:20Z","title":"Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21523","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":"sha256:3e6f6001ac6cf070a2afd177d964fb1d24d70e4e90c2e4425df1907f48a0e06c","target":"record","created_at":"2026-07-05T08:50:40Z","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":"bfc6350adac978400f7fd3b3912907608c02e6dfc9c4f93eb96c41447a06e594","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-31T10:56:20Z","title_canon_sha256":"5b78c399df119e03b73f77bbeea374359ad4c00f4b3fc814918c0698a2f22957"},"schema_version":"1.0","source":{"id":"2407.21523","kind":"arxiv","version":1}},"canonical_sha256":"c1cea247792b230e2d06632d92a8627304f2384d62b52fb78d1b9ced0fa68724","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1cea247792b230e2d06632d92a8627304f2384d62b52fb78d1b9ced0fa68724","first_computed_at":"2026-07-05T08:50:40.293409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:40.293409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e5T7RCk8pmdto5+xFJNHm/lnV5mZazF0np5N0x8uuQv8EaQw2YLSDQolbslEEVRVo4ucCjlIgS3J9YXtImm7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:40.293855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e6f6001ac6cf070a2afd177d964fb1d24d70e4e90c2e4425df1907f48a0e06c","sha256:6f65e25a84775f00c292d802e2c158ba7297fbad3279164a327d5017a23ac289"],"state_sha256":"6da41f1c41a6dc06b3f6bd1b1d31c5f98dbe9652e013c4783f23df67bff225f3"}