{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y6MDVYYEU4JJL4SXM4GIUY2JS7","short_pith_number":"pith:Y6MDVYYE","schema_version":"1.0","canonical_sha256":"c7983ae304a71295f257670c8a634997ec5d5c51a77c1bf835db284e6de6f7c9","source":{"kind":"arxiv","id":"2309.09968","version":3},"attestation_state":"computed","paper":{"title":"Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexia Jolicoeur-Martineau, Kilian Fatras, Tal Kachman","submitted_at":"2023-09-18T17:49:09Z","abstract_excerpt":"Tabular data is hard to acquire and is subject to missing values. This paper introduces a novel approach for generating and imputing mixed-type (continuous and categorical) tabular data utilizing score-based diffusion and conditional flow matching. In contrast to prior methods that rely on neural networks to learn the score function or the vector field, we adopt XGBoost, a widely used Gradient-Boosted Tree (GBT) technique. To test our method, we build one of the most extensive benchmarks for tabular data generation and imputation, containing 27 diverse datasets and 9 metrics. Through empirical"},"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":"2309.09968","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-18T17:49:09Z","cross_cats_sorted":[],"title_canon_sha256":"99d0797c883fb174e2ff700f3d544fd35a0e2aba2997384dd826d2215cbf3a2a","abstract_canon_sha256":"76259af7b9347e3a3fe6e2f83280c0b43afdf27efd7db0838f72d8090bf9aadc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:04.891748Z","signature_b64":"HWCzafPN0ZOU+vYTVX9VIrteZS0fgAK6W5Z5rNwTPXmnPFFqvRtVUwSPljqHa8NVXNtui9KVO+AogJrYYfoAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7983ae304a71295f257670c8a634997ec5d5c51a77c1bf835db284e6de6f7c9","last_reissued_at":"2026-07-05T07:47:04.891332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:04.891332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexia Jolicoeur-Martineau, Kilian Fatras, Tal Kachman","submitted_at":"2023-09-18T17:49:09Z","abstract_excerpt":"Tabular data is hard to acquire and is subject to missing values. This paper introduces a novel approach for generating and imputing mixed-type (continuous and categorical) tabular data utilizing score-based diffusion and conditional flow matching. In contrast to prior methods that rely on neural networks to learn the score function or the vector field, we adopt XGBoost, a widely used Gradient-Boosted Tree (GBT) technique. To test our method, we build one of the most extensive benchmarks for tabular data generation and imputation, containing 27 diverse datasets and 9 metrics. Through empirical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09968","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/2309.09968/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":"2309.09968","created_at":"2026-07-05T07:47:04.891391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09968v3","created_at":"2026-07-05T07:47:04.891391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09968","created_at":"2026-07-05T07:47:04.891391+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6MDVYYEU4JJ","created_at":"2026-07-05T07:47:04.891391+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6MDVYYEU4JJL4SX","created_at":"2026-07-05T07:47:04.891391+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6MDVYYE","created_at":"2026-07-05T07:47:04.891391+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":114,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7","json":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7.json","graph_json":"https://pith.science/api/pith-number/Y6MDVYYEU4JJL4SXM4GIUY2JS7/graph.json","events_json":"https://pith.science/api/pith-number/Y6MDVYYEU4JJL4SXM4GIUY2JS7/events.json","paper":"https://pith.science/paper/Y6MDVYYE"},"agent_actions":{"view_html":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7","download_json":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7.json","view_paper":"https://pith.science/paper/Y6MDVYYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09968&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6MDVYYEU4JJL4SXM4GIUY2JS7/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6MDVYYEU4JJL4SXM4GIUY2JS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/action/storage_attestation","attest_author":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/action/author_attestation","sign_citation":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/action/citation_signature","submit_replication":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/action/replication_record"}},"created_at":"2026-07-05T07:47:04.891391+00:00","updated_at":"2026-07-05T07:47:04.891391+00:00"}