{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y6MDVYYEU4JJL4SXM4GIUY2JS7","short_pith_number":"pith:Y6MDVYYE","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"},"canonical_sha256":"c7983ae304a71295f257670c8a634997ec5d5c51a77c1bf835db284e6de6f7c9","source":{"kind":"arxiv","id":"2309.09968","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09968","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09968v3","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09968","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"pith_short_12","alias_value":"Y6MDVYYEU4JJ","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y6MDVYYEU4JJL4SX","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y6MDVYYE","created_at":"2026-07-05T07:47:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y6MDVYYEU4JJL4SXM4GIUY2JS7","target":"record","payload":{"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"},"canonical_sha256":"c7983ae304a71295f257670c8a634997ec5d5c51a77c1bf835db284e6de6f7c9","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"},"source_kind":"arxiv","source_id":"2309.09968","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":"2026-07-05T07:47:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U4at1GaQesYBd+9+NeaT7q18/QAaL+ZXE+oNFn7thF3BAJvHXBZJ+7dYQLykaCA1HZzNDvWhDH3ruoOXmjEEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:40:53.530578Z"},"content_sha256":"ca8d3aff6554beddd9d25aa44f7afe849eb5fd55935ce48d6a5311e6fd402c14","schema_version":"1.0","event_id":"sha256:ca8d3aff6554beddd9d25aa44f7afe849eb5fd55935ce48d6a5311e6fd402c14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y6MDVYYEU4JJL4SXM4GIUY2JS7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:47:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GoQdcv3FdDHR97u2HjaR7M/BSx+NjuGM4oE7kzeuDGzNjfcqKCt/iG1aeId3/Y69q2ago7tn+ttc0wD0m8LkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:40:53.531620Z"},"content_sha256":"12619656738c39275096bae6815415e93eea0d0eb1664e85c619cc5ca9d4fd50","schema_version":"1.0","event_id":"sha256:12619656738c39275096bae6815415e93eea0d0eb1664e85c619cc5ca9d4fd50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/bundle.json","state_url":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/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":"2026-08-09T17:40:53Z","links":{"resolver":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7","bundle":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/bundle.json","state":"https://pith.science/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y6MDVYYEU4JJL4SXM4GIUY2JS7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y6MDVYYEU4JJL4SXM4GIUY2JS7","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":"76259af7b9347e3a3fe6e2f83280c0b43afdf27efd7db0838f72d8090bf9aadc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-18T17:49:09Z","title_canon_sha256":"99d0797c883fb174e2ff700f3d544fd35a0e2aba2997384dd826d2215cbf3a2a"},"schema_version":"1.0","source":{"id":"2309.09968","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09968","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09968v3","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09968","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"pith_short_12","alias_value":"Y6MDVYYEU4JJ","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y6MDVYYEU4JJL4SX","created_at":"2026-07-05T07:47:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y6MDVYYE","created_at":"2026-07-05T07:47:04Z"}],"graph_snapshots":[{"event_id":"sha256:12619656738c39275096bae6815415e93eea0d0eb1664e85c619cc5ca9d4fd50","target":"graph","created_at":"2026-07-05T07:47:04Z","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/2309.09968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexia Jolicoeur-Martineau, Kilian Fatras, Tal Kachman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-18T17:49:09Z","title":"Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09968","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:ca8d3aff6554beddd9d25aa44f7afe849eb5fd55935ce48d6a5311e6fd402c14","target":"record","created_at":"2026-07-05T07:47:04Z","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":"76259af7b9347e3a3fe6e2f83280c0b43afdf27efd7db0838f72d8090bf9aadc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-18T17:49:09Z","title_canon_sha256":"99d0797c883fb174e2ff700f3d544fd35a0e2aba2997384dd826d2215cbf3a2a"},"schema_version":"1.0","source":{"id":"2309.09968","kind":"arxiv","version":3}},"canonical_sha256":"c7983ae304a71295f257670c8a634997ec5d5c51a77c1bf835db284e6de6f7c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7983ae304a71295f257670c8a634997ec5d5c51a77c1bf835db284e6de6f7c9","first_computed_at":"2026-07-05T07:47:04.891332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:04.891332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HWCzafPN0ZOU+vYTVX9VIrteZS0fgAK6W5Z5rNwTPXmnPFFqvRtVUwSPljqHa8NVXNtui9KVO+AogJrYYfoAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:04.891748Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.09968","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca8d3aff6554beddd9d25aa44f7afe849eb5fd55935ce48d6a5311e6fd402c14","sha256:12619656738c39275096bae6815415e93eea0d0eb1664e85c619cc5ca9d4fd50"],"state_sha256":"7827523f06f899f23ad4b0d2cbb7319f53b2355a4f63259f5357bd0e5437e338"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBv3N1t6BQ4rYBpWCig68E3i6Fq1z32KYYtZIGtGMTX1bFfohItkBeTvX/ZEtWqJRN60sNbprWi/bZcJnqTkDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:40:53.538753Z","bundle_sha256":"c1cfdb173f7cfccfad7f0197d43e444f781b0e8923294e867831607f90893a47"}}