{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:B5YA6CSKJIVSC3FRGGK7AXWB74","short_pith_number":"pith:B5YA6CSK","canonical_record":{"source":{"id":"2504.16506","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-23T08:33:34Z","cross_cats_sorted":[],"title_canon_sha256":"4babbf1dbd99fe0f038606262172431bffa817d9a1aed019ba516116da2915d3","abstract_canon_sha256":"cd41cc0a31c3e79197b44fb49cf2c442d72ed30fcdab400abfd6ca3c138a77ab"},"schema_version":"1.0"},"canonical_sha256":"0f700f0a4a4a2b216cb13195f05ec1ff26af49042d750537e6151233b4920cd5","source":{"kind":"arxiv","id":"2504.16506","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16506","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16506v3","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16506","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"B5YA6CSKJIVS","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"B5YA6CSKJIVSC3FR","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"B5YA6CSK","created_at":"2026-07-05T11:38:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:B5YA6CSKJIVSC3FRGGK7AXWB74","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16506","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-23T08:33:34Z","cross_cats_sorted":[],"title_canon_sha256":"4babbf1dbd99fe0f038606262172431bffa817d9a1aed019ba516116da2915d3","abstract_canon_sha256":"cd41cc0a31c3e79197b44fb49cf2c442d72ed30fcdab400abfd6ca3c138a77ab"},"schema_version":"1.0"},"canonical_sha256":"0f700f0a4a4a2b216cb13195f05ec1ff26af49042d750537e6151233b4920cd5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:28.977202Z","signature_b64":"IMmAVUoPkgzE6nPy0WRy3lI7x3T6kraTUUvx4XH3m3O20srJ5Bw+n/oNQz2pqIVbhLOfFaQTQpOfuDtfKLfFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f700f0a4a4a2b216cb13195f05ec1ff26af49042d750537e6151233b4920cd5","last_reissued_at":"2026-07-05T11:38:28.976690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:28.976690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16506","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:38:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQnhhAvvLG8VH9WUk8kn28NMBbliBi/TwKV9FLHXqWVOzel3qgJpUqJ23SpUCUTx6+Zhne/clUx7Jhty7omZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T13:11:41.229469Z"},"content_sha256":"7a608d9f61b05a0386908cfb7d42608bd00dce7b2ee9cf2f18d5785d464583ab","schema_version":"1.0","event_id":"sha256:7a608d9f61b05a0386908cfb7d42608bd00dce7b2ee9cf2f18d5785d464583ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:B5YA6CSKJIVSC3FRGGK7AXWB74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comprehensive Survey of Synthetic Tabular Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mengnan Du, Ruxue Shi, Xin Wang, Xu Shen, Yi Chang, Yili Wang","submitted_at":"2025-04-23T08:33:34Z","abstract_excerpt":"Tabular data is one of the most prevalent and important data formats in real-world applications such as healthcare, finance, and education. However, its effective use in machine learning is often constrained by data scarcity, privacy concerns, and class imbalance. Synthetic tabular data generation has emerged as a powerful solution, leveraging generative models to learn underlying data distributions and produce realistic, privacy-preserving samples. Although this area has seen growing attention, most existing surveys focus narrowly on specific methods (e.g., GANs or privacy-enhancing technique"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16506","kind":"arxiv","version":3},"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/2504.16506/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":"2026-07-05T11:38:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qJCkdg13j7GOMaSy5YHulJrm/zjs+jobSDvJghxkj/cdoFep59MM28iU7Mdu7AsuiX7XmTlbyY4ouCMgDm2aAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T13:11:41.230458Z"},"content_sha256":"4dc13e38e2de27f564ee578c716da0fbe989b6611c8f30013c878c510aaf1818","schema_version":"1.0","event_id":"sha256:4dc13e38e2de27f564ee578c716da0fbe989b6611c8f30013c878c510aaf1818"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B5YA6CSKJIVSC3FRGGK7AXWB74/bundle.json","state_url":"https://pith.science/pith/B5YA6CSKJIVSC3FRGGK7AXWB74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B5YA6CSKJIVSC3FRGGK7AXWB74/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":"2026-08-07T13:11:41Z","links":{"resolver":"https://pith.science/pith/B5YA6CSKJIVSC3FRGGK7AXWB74","bundle":"https://pith.science/pith/B5YA6CSKJIVSC3FRGGK7AXWB74/bundle.json","state":"https://pith.science/pith/B5YA6CSKJIVSC3FRGGK7AXWB74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B5YA6CSKJIVSC3FRGGK7AXWB74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B5YA6CSKJIVSC3FRGGK7AXWB74","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":"cd41cc0a31c3e79197b44fb49cf2c442d72ed30fcdab400abfd6ca3c138a77ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-23T08:33:34Z","title_canon_sha256":"4babbf1dbd99fe0f038606262172431bffa817d9a1aed019ba516116da2915d3"},"schema_version":"1.0","source":{"id":"2504.16506","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16506","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16506v3","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16506","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"B5YA6CSKJIVS","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"B5YA6CSKJIVSC3FR","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"B5YA6CSK","created_at":"2026-07-05T11:38:28Z"}],"graph_snapshots":[{"event_id":"sha256:4dc13e38e2de27f564ee578c716da0fbe989b6611c8f30013c878c510aaf1818","target":"graph","created_at":"2026-07-05T11:38:28Z","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/2504.16506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data is one of the most prevalent and important data formats in real-world applications such as healthcare, finance, and education. However, its effective use in machine learning is often constrained by data scarcity, privacy concerns, and class imbalance. Synthetic tabular data generation has emerged as a powerful solution, leveraging generative models to learn underlying data distributions and produce realistic, privacy-preserving samples. Although this area has seen growing attention, most existing surveys focus narrowly on specific methods (e.g., GANs or privacy-enhancing technique","authors_text":"Mengnan Du, Ruxue Shi, Xin Wang, Xu Shen, Yi Chang, Yili Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-23T08:33:34Z","title":"A Comprehensive Survey of Synthetic Tabular Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16506","kind":"arxiv","version":3},"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":"sha256:7a608d9f61b05a0386908cfb7d42608bd00dce7b2ee9cf2f18d5785d464583ab","target":"record","created_at":"2026-07-05T11:38:28Z","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":"cd41cc0a31c3e79197b44fb49cf2c442d72ed30fcdab400abfd6ca3c138a77ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-23T08:33:34Z","title_canon_sha256":"4babbf1dbd99fe0f038606262172431bffa817d9a1aed019ba516116da2915d3"},"schema_version":"1.0","source":{"id":"2504.16506","kind":"arxiv","version":3}},"canonical_sha256":"0f700f0a4a4a2b216cb13195f05ec1ff26af49042d750537e6151233b4920cd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f700f0a4a4a2b216cb13195f05ec1ff26af49042d750537e6151233b4920cd5","first_computed_at":"2026-07-05T11:38:28.976690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:28.976690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IMmAVUoPkgzE6nPy0WRy3lI7x3T6kraTUUvx4XH3m3O20srJ5Bw+n/oNQz2pqIVbhLOfFaQTQpOfuDtfKLfFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:28.977202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16506","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a608d9f61b05a0386908cfb7d42608bd00dce7b2ee9cf2f18d5785d464583ab","sha256:4dc13e38e2de27f564ee578c716da0fbe989b6611c8f30013c878c510aaf1818"],"state_sha256":"53a36e2af65cc071189789f5595026d5c2823e0444d0b0efae2cb3642e6f49de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rWNVZCmo2U+jA0C5ljg5BLcGIhrOipqZ+eD6YQkP9J81tCm+y014GDiUtdsvnO0Ag0rqRIAn6NtVSR8F6aBADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T13:11:41.235577Z","bundle_sha256":"d3e280fcf4ae6206db4ea6a3d9b57a84d720df66ec2429e3e9041a6d7c9b89d7"}}