{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3IWZVSWKSFFNZRI77LTPIZCXAK","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":"a90bfd55e98697cb639a3cc023aeff1d910b56306380ec0098ebf40e0cf22398","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T09:15:22Z","title_canon_sha256":"45a71eea9b71629090a9adb3c3e68dd65f7a65062c3f949acbc34ca802a2b653"},"schema_version":"1.0","source":{"id":"2507.10088","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10088","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10088v1","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10088","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"pith_short_12","alias_value":"3IWZVSWKSFFN","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"pith_short_16","alias_value":"3IWZVSWKSFFNZRI7","created_at":"2026-07-05T11:36:44Z"},{"alias_kind":"pith_short_8","alias_value":"3IWZVSWK","created_at":"2026-07-05T11:36:44Z"}],"graph_snapshots":[{"event_id":"sha256:42293ca97f051ee67c68db9122b63989c7888ef81f1c94877cb91d2785346ff9","target":"graph","created_at":"2026-07-05T11:36:44Z","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/2507.10088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data synthesis for supervised learning ('SL') model training is gaining popularity in industries such as healthcare, finance, and retail. Despite the progress made in tabular data generators, models trained with synthetic data often underperform compared to those trained with original data. This low SL utility of synthetic data stems from class imbalance exaggeration and SL data relationship overlooked by tabular generator. To address these challenges, we draw inspirations from techniques in emerging data-centric artificial intelligence and elucidate Pruning and ReOrdering ('PRRO'), a ","authors_text":"Chi-Hua Wang, Guang Cheng, Tung Sum Thomas Kwok, Zeyong Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T09:15:22Z","title":"Towards High Supervised Learning Utility Training Data Generation: Data Pruning and Column Reordering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10088","kind":"arxiv","version":1},"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:c26f48c7bfe6153e77762d3ec18097d1be0417bafe97718e876584e56db4ccc8","target":"record","created_at":"2026-07-05T11:36:44Z","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":"a90bfd55e98697cb639a3cc023aeff1d910b56306380ec0098ebf40e0cf22398","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T09:15:22Z","title_canon_sha256":"45a71eea9b71629090a9adb3c3e68dd65f7a65062c3f949acbc34ca802a2b653"},"schema_version":"1.0","source":{"id":"2507.10088","kind":"arxiv","version":1}},"canonical_sha256":"da2d9acaca914adcc51ffae6f4645702942c2958d2566e377dbb76af1f24ea8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da2d9acaca914adcc51ffae6f4645702942c2958d2566e377dbb76af1f24ea8f","first_computed_at":"2026-07-05T11:36:44.748407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:44.748407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NU/xseox45JWXkEaqg3XQksVezmIQVzV97VLDAeMFMdyZIfn1qg4lo1LGFtwtOZIh1yRNg/IJ/iy+ihtPb/+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:44.748983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10088","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c26f48c7bfe6153e77762d3ec18097d1be0417bafe97718e876584e56db4ccc8","sha256:42293ca97f051ee67c68db9122b63989c7888ef81f1c94877cb91d2785346ff9"],"state_sha256":"f59ca8f353b9cf3219dfa2da42b292d27df2430020f3d91d776dcca196870b71"}