{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y7YM2HZRT5RRLOYWRKTUPXK7PD","short_pith_number":"pith:Y7YM2HZR","schema_version":"1.0","canonical_sha256":"c7f0cd1f319f6315bb168aa747dd5f78e3c04b5c6dbfca446ae5fa1fb001089c","source":{"kind":"arxiv","id":"2507.19211","version":1},"attestation_state":"computed","paper":{"title":"Dependency-aware synthetic tabular data generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaithra Umesh, Kristian Schultz, Manjunath Mahendra, Olaf Wolkenhauer, Saptarshi Bej","submitted_at":"2025-07-25T12:29:58Z","abstract_excerpt":"Synthetic tabular data is increasingly used in privacy-sensitive domains such as health care, but existing generative models often fail to preserve inter-attribute relationships. In particular, functional dependencies (FDs) and logical dependencies (LDs), which capture deterministic and rule-based associations between features, are rarely or often poorly retained in synthetic datasets. To address this research gap, we propose the Hierarchical Feature Generation Framework (HFGF) for synthetic tabular data generation. We created benchmark datasets with known dependencies to evaluate our proposed"},"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":"2507.19211","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T12:29:58Z","cross_cats_sorted":[],"title_canon_sha256":"7a5502a223cdcef3c3c3a08bfc68382bf6d41911f511c1cf00e64b543a911f61","abstract_canon_sha256":"4a320773c98e71b6b12ee6903afd991d2ce9bd40f008b1d1008289be0028ba6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:21.495049Z","signature_b64":"F39nkifWaK/V/NyouIe7qoCgks+q0lYHdldpJkpThYNaIyXnELn9LRgsqPF6re2cG1S4pYqwqKDnovuGk6iBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7f0cd1f319f6315bb168aa747dd5f78e3c04b5c6dbfca446ae5fa1fb001089c","last_reissued_at":"2026-07-05T11:43:21.494575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:21.494575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dependency-aware synthetic tabular data generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaithra Umesh, Kristian Schultz, Manjunath Mahendra, Olaf Wolkenhauer, Saptarshi Bej","submitted_at":"2025-07-25T12:29:58Z","abstract_excerpt":"Synthetic tabular data is increasingly used in privacy-sensitive domains such as health care, but existing generative models often fail to preserve inter-attribute relationships. In particular, functional dependencies (FDs) and logical dependencies (LDs), which capture deterministic and rule-based associations between features, are rarely or often poorly retained in synthetic datasets. To address this research gap, we propose the Hierarchical Feature Generation Framework (HFGF) for synthetic tabular data generation. We created benchmark datasets with known dependencies to evaluate our proposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19211","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/2507.19211/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":"2507.19211","created_at":"2026-07-05T11:43:21.494633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19211v1","created_at":"2026-07-05T11:43:21.494633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19211","created_at":"2026-07-05T11:43:21.494633+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7YM2HZRT5RR","created_at":"2026-07-05T11:43:21.494633+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7YM2HZRT5RRLOYW","created_at":"2026-07-05T11:43:21.494633+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7YM2HZR","created_at":"2026-07-05T11:43:21.494633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7YM2HZRT5RRLOYWRKTUPXK7PD","json":"https://pith.science/pith/Y7YM2HZRT5RRLOYWRKTUPXK7PD.json","graph_json":"https://pith.science/api/pith-number/Y7YM2HZRT5RRLOYWRKTUPXK7PD/graph.json","events_json":"https://pith.science/api/pith-number/Y7YM2HZRT5RRLOYWRKTUPXK7PD/events.json","paper":"https://pith.science/paper/Y7YM2HZR"},"agent_actions":{"view_html":"https://pith.science/pith/Y7YM2HZRT5RRLOYWRKTUPXK7PD","download_json":"https://pith.science/pith/Y7YM2HZRT5RRLOYWRKTUPXK7PD.json","view_paper":"https://pith.science/paper/Y7YM2HZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19211&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7YM2HZRT5RRLOYWRKTUPXK7PD/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7YM2HZRT5RRLOYWRKTUPXK7PD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7YM2HZRT5RRLOYWRKTUPXK7PD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7YM2HZRT5RRLOYWRKTUPXK7PD/action/storage_attestation","attest_author":"https://pith.science/pith/Y7YM2HZRT5RRLOYWRKTUPXK7PD/action/author_attestation","sign_citation":"https://pith.science/pith/Y7YM2HZRT5RRLOYWRKTUPXK7PD/action/citation_signature","submit_replication":"https://pith.science/pith/Y7YM2HZRT5RRLOYWRKTUPXK7PD/action/replication_record"}},"created_at":"2026-07-05T11:43:21.494633+00:00","updated_at":"2026-07-05T11:43:21.494633+00:00"}