{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YHHKER3ZFMRQ4LIGMMWZFKDCOM","short_pith_number":"pith:YHHKER3Z","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"},"canonical_sha256":"c1cea247792b230e2d06632d92a8627304f2384d62b52fb78d1b9ced0fa68724","source":{"kind":"arxiv","id":"2407.21523","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YHHKER3ZFMRQ4LIGMMWZFKDCOM","target":"record","payload":{"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"},"canonical_sha256":"c1cea247792b230e2d06632d92a8627304f2384d62b52fb78d1b9ced0fa68724","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"},"source_kind":"arxiv","source_id":"2407.21523","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":"2026-07-05T08:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Yb8bEd0FhHw41LLsypEIZkv0p0nl/7Wski0hUv0iG2l9HIhiBveozEY1bxklMAzrmJ/3fEt54ijSv779QguDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:37:32.793323Z"},"content_sha256":"3e6f6001ac6cf070a2afd177d964fb1d24d70e4e90c2e4425df1907f48a0e06c","schema_version":"1.0","event_id":"sha256:3e6f6001ac6cf070a2afd177d964fb1d24d70e4e90c2e4425df1907f48a0e06c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YHHKER3ZFMRQ4LIGMMWZFKDCOM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:50:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGaLPI4aeVwjqVWct/oTY20x51eBXbKBmqJiFupzjxCoVVNix94/49U2nD+3bzDi2T84rf7rSOQ8S26odSTkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:37:32.793708Z"},"content_sha256":"6f65e25a84775f00c292d802e2c158ba7297fbad3279164a327d5017a23ac289","schema_version":"1.0","event_id":"sha256:6f65e25a84775f00c292d802e2c158ba7297fbad3279164a327d5017a23ac289"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/bundle.json","state_url":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/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":"2026-08-07T07:37:32Z","links":{"resolver":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM","bundle":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/bundle.json","state":"https://pith.science/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YHHKER3ZFMRQ4LIGMMWZFKDCOM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKUR8xXFkRywsUP+zAr69I+n1LpDzGCn+pPbmFett9lwb0i5nmWpJISazCpD2rsqqDzDfCur3x3AX0griq8GAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:37:32.796452Z","bundle_sha256":"82f86f7acaf1adfd19971985c6ba32f5b6d4ce05b1797ce477965c0f9f826136"}}