{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YHHKER3ZFMRQ4LIGMMWZFKDCOM","short_pith_number":"pith:YHHKER3Z","schema_version":"1.0","canonical_sha256":"c1cea247792b230e2d06632d92a8627304f2384d62b52fb78d1b9ced0fa68724","source":{"kind":"arxiv","id":"2407.21523","version":1},"attestation_state":"computed","paper":{"title":"Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Gang Chen, Huan Li, Ke Chen, Lidan Shou, Lingxi Cui","submitted_at":"2024-07-31T10:56:20Z","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"},"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":"2407.21523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-31T10:56:20Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"5b78c399df119e03b73f77bbeea374359ad4c00f4b3fc814918c0698a2f22957","abstract_canon_sha256":"bfc6350adac978400f7fd3b3912907608c02e6dfc9c4f93eb96c41447a06e594"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:40.293855Z","signature_b64":"e5T7RCk8pmdto5+xFJNHm/lnV5mZazF0np5N0x8uuQv8EaQw2YLSDQolbslEEVRVo4ucCjlIgS3J9YXtImm7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1cea247792b230e2d06632d92a8627304f2384d62b52fb78d1b9ced0fa68724","last_reissued_at":"2026-07-05T08:50:40.293409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:40.293409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Gang Chen, Huan Li, Ke Chen, Lidan Shou, Lingxi Cui","submitted_at":"2024-07-31T10:56:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21523","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/2407.21523/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":"2407.21523","created_at":"2026-07-05T08:50:40.293472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21523v1","created_at":"2026-07-05T08:50:40.293472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21523","created_at":"2026-07-05T08:50:40.293472+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHHKER3ZFMRQ","created_at":"2026-07-05T08:50:40.293472+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHHKER3ZFMRQ4LIG","created_at":"2026-07-05T08:50:40.293472+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHHKER3Z","created_at":"2026-07-05T08:50:40.293472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.17119","citing_title":"Diffusion and Flow Matching Models for Tabular Data: A Survey","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13657","citing_title":"In-Context Decision Making for Optimizing Complex AutoML Pipelines","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10315","citing_title":"Active Tabular Augmentation via Policy-Guided Diffusion Inpainting","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM","json":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM.json","graph_json":"https://pith.science/api/pith-number/YHHKER3ZFMRQ4LIGMMWZFKDCOM/graph.json","events_json":"https://pith.science/api/pith-number/YHHKER3ZFMRQ4LIGMMWZFKDCOM/events.json","paper":"https://pith.science/paper/YHHKER3Z"},"agent_actions":{"view_html":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM","download_json":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM.json","view_paper":"https://pith.science/paper/YHHKER3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21523&json=true","fetch_graph":"https://pith.science/api/pith-number/YHHKER3ZFMRQ4LIGMMWZFKDCOM/graph.json","fetch_events":"https://pith.science/api/pith-number/YHHKER3ZFMRQ4LIGMMWZFKDCOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/action/storage_attestation","attest_author":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/action/author_attestation","sign_citation":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/action/citation_signature","submit_replication":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/action/replication_record"}},"created_at":"2026-07-05T08:50:40.293472+00:00","updated_at":"2026-07-05T08:50:40.293472+00:00"}