{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GWI3IVCBSPPCXFBIRTLG5E7KTG","short_pith_number":"pith:GWI3IVCB","schema_version":"1.0","canonical_sha256":"3591b4544193de2b94288cd66e93ea99afc16ec5a69558ed9dfb4aad23d3c2dd","source":{"kind":"arxiv","id":"2307.03577","version":4},"attestation_state":"computed","paper":{"title":"CuTS: Customizable Tabular Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.PL"],"primary_cat":"cs.LG","authors_text":"Mark Vero, Martin Vechev, Mislav Balunovi\\'c","submitted_at":"2023-07-07T13:10:23Z","abstract_excerpt":"Privacy, data quality, and data sharing concerns pose a key limitation for tabular data applications. While generating synthetic data resembling the original distribution addresses some of these issues, most applications would benefit from additional customization on the generated data. However, existing synthetic data approaches are limited to particular constraints, e.g., differential privacy (DP) or fairness. In this work, we introduce CuTS, the first customizable synthetic tabular data generation framework. Customization in CuTS is achieved via declarative statistical and logical expressio"},"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":"2307.03577","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-07T13:10:23Z","cross_cats_sorted":["cs.DB","cs.PL"],"title_canon_sha256":"1f6b1b140255cfaa436b934ba67302fb56718a991e58526a3d6c8e4dfa9eeedd","abstract_canon_sha256":"b1c28a1af62e77d64f4cda1757569dcce5b48e69d2cf92cbd5e4c9a382a9aa7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:12.704492Z","signature_b64":"2LJb3FLdBkH8kZhCn4DV7OL6RwMLDIcqHphsjUs1hp7DyTW3YJy9W9CG/GYp6XIbenx/9UDJKOd238eAb1NbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3591b4544193de2b94288cd66e93ea99afc16ec5a69558ed9dfb4aad23d3c2dd","last_reissued_at":"2026-07-05T08:26:12.703958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:12.703958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CuTS: Customizable Tabular Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.PL"],"primary_cat":"cs.LG","authors_text":"Mark Vero, Martin Vechev, Mislav Balunovi\\'c","submitted_at":"2023-07-07T13:10:23Z","abstract_excerpt":"Privacy, data quality, and data sharing concerns pose a key limitation for tabular data applications. While generating synthetic data resembling the original distribution addresses some of these issues, most applications would benefit from additional customization on the generated data. However, existing synthetic data approaches are limited to particular constraints, e.g., differential privacy (DP) or fairness. In this work, we introduce CuTS, the first customizable synthetic tabular data generation framework. Customization in CuTS is achieved via declarative statistical and logical expressio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03577","kind":"arxiv","version":4},"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/2307.03577/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":"2307.03577","created_at":"2026-07-05T08:26:12.704020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03577v4","created_at":"2026-07-05T08:26:12.704020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03577","created_at":"2026-07-05T08:26:12.704020+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWI3IVCBSPPC","created_at":"2026-07-05T08:26:12.704020+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWI3IVCBSPPCXFBI","created_at":"2026-07-05T08:26:12.704020+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWI3IVCB","created_at":"2026-07-05T08:26:12.704020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWI3IVCBSPPCXFBIRTLG5E7KTG","json":"https://pith.science/pith/GWI3IVCBSPPCXFBIRTLG5E7KTG.json","graph_json":"https://pith.science/api/pith-number/GWI3IVCBSPPCXFBIRTLG5E7KTG/graph.json","events_json":"https://pith.science/api/pith-number/GWI3IVCBSPPCXFBIRTLG5E7KTG/events.json","paper":"https://pith.science/paper/GWI3IVCB"},"agent_actions":{"view_html":"https://pith.science/pith/GWI3IVCBSPPCXFBIRTLG5E7KTG","download_json":"https://pith.science/pith/GWI3IVCBSPPCXFBIRTLG5E7KTG.json","view_paper":"https://pith.science/paper/GWI3IVCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03577&json=true","fetch_graph":"https://pith.science/api/pith-number/GWI3IVCBSPPCXFBIRTLG5E7KTG/graph.json","fetch_events":"https://pith.science/api/pith-number/GWI3IVCBSPPCXFBIRTLG5E7KTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWI3IVCBSPPCXFBIRTLG5E7KTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWI3IVCBSPPCXFBIRTLG5E7KTG/action/storage_attestation","attest_author":"https://pith.science/pith/GWI3IVCBSPPCXFBIRTLG5E7KTG/action/author_attestation","sign_citation":"https://pith.science/pith/GWI3IVCBSPPCXFBIRTLG5E7KTG/action/citation_signature","submit_replication":"https://pith.science/pith/GWI3IVCBSPPCXFBIRTLG5E7KTG/action/replication_record"}},"created_at":"2026-07-05T08:26:12.704020+00:00","updated_at":"2026-07-05T08:26:12.704020+00:00"}