{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JF5JVZHOW6ONRY4BLRHR7IILZT","short_pith_number":"pith:JF5JVZHO","schema_version":"1.0","canonical_sha256":"497a9ae4eeb79cd8e3815c4f1fa10bccfacdb30c270c2ff9b2473896790d0e9b","source":{"kind":"arxiv","id":"2501.12012","version":2},"attestation_state":"computed","paper":{"title":"TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Sidorenko, Ivona Krchova, Mariana Vargas Vieyra, Mario Scriminaci, Michael Platzer, Paul Tiwald","submitted_at":"2025-01-21T10:06:19Z","abstract_excerpt":"Synthetic data generation for tabular datasets must balance fidelity, efficiency, and versatility to meet the demands of real-world applications. We introduce the Tabular Auto-Regressive Generative Network (TabularARGN), a flexible framework designed to handle mixed-type, multivariate, and sequential datasets. By training on all possible conditional probabilities, TabularARGN supports advanced features such as fairness-aware generation, imputation, and conditional generation on any subset of columns. The framework achieves state-of-the-art synthetic data quality while significantly reducing tr"},"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":"2501.12012","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T10:06:19Z","cross_cats_sorted":[],"title_canon_sha256":"ace7b1699c4ee3f1d756dd27e064433ae3d6ac8879f85708c5169d106e11fe8e","abstract_canon_sha256":"b67eb1766cddf04b06cbebcd25e0e46685e9422fa32b648535bc9f4f5a787415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:29.724960Z","signature_b64":"wNgK4TImAKN5e2uA0SRLS7kq6iyhGMU7Pszm5eKThJIQKoFYjkKunXo9OB4DflvU881qumW3no0rBcoidkM1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"497a9ae4eeb79cd8e3815c4f1fa10bccfacdb30c270c2ff9b2473896790d0e9b","last_reissued_at":"2026-07-05T10:10:29.724554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:29.724554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Sidorenko, Ivona Krchova, Mariana Vargas Vieyra, Mario Scriminaci, Michael Platzer, Paul Tiwald","submitted_at":"2025-01-21T10:06:19Z","abstract_excerpt":"Synthetic data generation for tabular datasets must balance fidelity, efficiency, and versatility to meet the demands of real-world applications. We introduce the Tabular Auto-Regressive Generative Network (TabularARGN), a flexible framework designed to handle mixed-type, multivariate, and sequential datasets. By training on all possible conditional probabilities, TabularARGN supports advanced features such as fairness-aware generation, imputation, and conditional generation on any subset of columns. The framework achieves state-of-the-art synthetic data quality while significantly reducing tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12012","kind":"arxiv","version":2},"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/2501.12012/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":"2501.12012","created_at":"2026-07-05T10:10:29.724605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12012v2","created_at":"2026-07-05T10:10:29.724605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12012","created_at":"2026-07-05T10:10:29.724605+00:00"},{"alias_kind":"pith_short_12","alias_value":"JF5JVZHOW6ON","created_at":"2026-07-05T10:10:29.724605+00:00"},{"alias_kind":"pith_short_16","alias_value":"JF5JVZHOW6ONRY4B","created_at":"2026-07-05T10:10:29.724605+00:00"},{"alias_kind":"pith_short_8","alias_value":"JF5JVZHO","created_at":"2026-07-05T10:10:29.724605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01444","citing_title":"Autoregressive Synthesis of Sparse and Semi-Structured Mixed-Type Data","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09424","citing_title":"Tabular Foundation Model for Generative Modelling","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JF5JVZHOW6ONRY4BLRHR7IILZT","json":"https://pith.science/pith/JF5JVZHOW6ONRY4BLRHR7IILZT.json","graph_json":"https://pith.science/api/pith-number/JF5JVZHOW6ONRY4BLRHR7IILZT/graph.json","events_json":"https://pith.science/api/pith-number/JF5JVZHOW6ONRY4BLRHR7IILZT/events.json","paper":"https://pith.science/paper/JF5JVZHO"},"agent_actions":{"view_html":"https://pith.science/pith/JF5JVZHOW6ONRY4BLRHR7IILZT","download_json":"https://pith.science/pith/JF5JVZHOW6ONRY4BLRHR7IILZT.json","view_paper":"https://pith.science/paper/JF5JVZHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12012&json=true","fetch_graph":"https://pith.science/api/pith-number/JF5JVZHOW6ONRY4BLRHR7IILZT/graph.json","fetch_events":"https://pith.science/api/pith-number/JF5JVZHOW6ONRY4BLRHR7IILZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JF5JVZHOW6ONRY4BLRHR7IILZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JF5JVZHOW6ONRY4BLRHR7IILZT/action/storage_attestation","attest_author":"https://pith.science/pith/JF5JVZHOW6ONRY4BLRHR7IILZT/action/author_attestation","sign_citation":"https://pith.science/pith/JF5JVZHOW6ONRY4BLRHR7IILZT/action/citation_signature","submit_replication":"https://pith.science/pith/JF5JVZHOW6ONRY4BLRHR7IILZT/action/replication_record"}},"created_at":"2026-07-05T10:10:29.724605+00:00","updated_at":"2026-07-05T10:10:29.724605+00:00"}