{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2JIFUQNR76QD2G4LNUEKYDG3HU","short_pith_number":"pith:2JIFUQNR","canonical_record":{"source":{"id":"2501.10555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T21:05:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a50b3eaffff2a61577335de7af892635ae633d78848a1bf0b5a59ae65a10da0","abstract_canon_sha256":"d91b13ee6393b7dbd69a8f0fa853f6fe022c35d9a90706bfc0a5a69e4defb766"},"schema_version":"1.0"},"canonical_sha256":"d2505a41b1ffa03d1b8b6d08ac0cdb3d0eac636bbe18edb55f85f88813766950","source":{"kind":"arxiv","id":"2501.10555","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10555","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10555v1","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10555","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"2JIFUQNR76QD","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"2JIFUQNR76QD2G4L","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"2JIFUQNR","created_at":"2026-07-05T10:02:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2JIFUQNR76QD2G4LNUEKYDG3HU","target":"record","payload":{"canonical_record":{"source":{"id":"2501.10555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T21:05:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a50b3eaffff2a61577335de7af892635ae633d78848a1bf0b5a59ae65a10da0","abstract_canon_sha256":"d91b13ee6393b7dbd69a8f0fa853f6fe022c35d9a90706bfc0a5a69e4defb766"},"schema_version":"1.0"},"canonical_sha256":"d2505a41b1ffa03d1b8b6d08ac0cdb3d0eac636bbe18edb55f85f88813766950","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:29.809285Z","signature_b64":"MZt0WrRUNvLs/jaRpqVc+a61wfDgx4Bz9A035HKBpqV/RqglNpQULmDhA5qHtrfgijwq8FPtRr7ePhT1i+wADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2505a41b1ffa03d1b8b6d08ac0cdb3d0eac636bbe18edb55f85f88813766950","last_reissued_at":"2026-07-05T10:02:29.808801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:29.808801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.10555","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IQPWBlmPB/8Q+rXX5vVSibkQbwlQumLQV3+lcJ9SzTMfX803mWNQeGxaSS+OPI+9TcZ1Ex+1CRXfQz3LHZ8eDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:36:01.447295Z"},"content_sha256":"365602343cba78b621b64b8ec57e39f17bcb531ff2933374e50f96c97781f8b0","schema_version":"1.0","event_id":"sha256:365602343cba78b621b64b8ec57e39f17bcb531ff2933374e50f96c97781f8b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2JIFUQNR76QD2G4LNUEKYDG3HU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Data-Centric AI: A Comprehensive Survey of Traditional, Reinforcement, and Generative Approaches for Tabular Data Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongjie Wang, Haoyue Bai, Hui Xiong, Kunpeng Liu, Meng Xiao, Nanxu Gong, Pengfei Wang, Pengyang Wang, Sixun Dong, Tao Zhe, Wangyang Ying, Xinyuan Wang, Yanjie Fu, Yanyong Huang","submitted_at":"2025-01-17T21:05:09Z","abstract_excerpt":"Tabular data is one of the most widely used formats across industries, driving critical applications in areas such as finance, healthcare, and marketing. In the era of data-centric AI, improving data quality and representation has become essential for enhancing model performance, particularly in applications centered around tabular data. This survey examines the key aspects of tabular data-centric AI, emphasizing feature selection and feature generation as essential techniques for data space refinement. We provide a systematic review of feature selection methods, which identify and retain the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10555","kind":"arxiv","version":1},"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/2501.10555/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":"2026-07-05T10:02:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VXPqvJau15uMpNLIsSc1vxfj2aTwALXwm1zsOz8Uhzz6MLZKVopKWJrTXSz55K0rnXiBxxTUmHyDHhvOC7YHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:36:01.448110Z"},"content_sha256":"764797f209b14442cd01fa1f15e6fe24f396a9ff6e2b777061ac56a7ba9c44f3","schema_version":"1.0","event_id":"sha256:764797f209b14442cd01fa1f15e6fe24f396a9ff6e2b777061ac56a7ba9c44f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/bundle.json","state_url":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/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":"2026-08-10T07:36:01Z","links":{"resolver":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU","bundle":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/bundle.json","state":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2JIFUQNR76QD2G4LNUEKYDG3HU","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":"d91b13ee6393b7dbd69a8f0fa853f6fe022c35d9a90706bfc0a5a69e4defb766","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T21:05:09Z","title_canon_sha256":"0a50b3eaffff2a61577335de7af892635ae633d78848a1bf0b5a59ae65a10da0"},"schema_version":"1.0","source":{"id":"2501.10555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10555","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10555v1","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10555","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"pith_short_12","alias_value":"2JIFUQNR76QD","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"pith_short_16","alias_value":"2JIFUQNR76QD2G4L","created_at":"2026-07-05T10:02:29Z"},{"alias_kind":"pith_short_8","alias_value":"2JIFUQNR","created_at":"2026-07-05T10:02:29Z"}],"graph_snapshots":[{"event_id":"sha256:764797f209b14442cd01fa1f15e6fe24f396a9ff6e2b777061ac56a7ba9c44f3","target":"graph","created_at":"2026-07-05T10:02:29Z","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/2501.10555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data is one of the most widely used formats across industries, driving critical applications in areas such as finance, healthcare, and marketing. In the era of data-centric AI, improving data quality and representation has become essential for enhancing model performance, particularly in applications centered around tabular data. This survey examines the key aspects of tabular data-centric AI, emphasizing feature selection and feature generation as essential techniques for data space refinement. We provide a systematic review of feature selection methods, which identify and retain the ","authors_text":"Dongjie Wang, Haoyue Bai, Hui Xiong, Kunpeng Liu, Meng Xiao, Nanxu Gong, Pengfei Wang, Pengyang Wang, Sixun Dong, Tao Zhe, Wangyang Ying, Xinyuan Wang, Yanjie Fu, Yanyong Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T21:05:09Z","title":"Towards Data-Centric AI: A Comprehensive Survey of Traditional, Reinforcement, and Generative Approaches for Tabular Data Transformation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10555","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":"sha256:365602343cba78b621b64b8ec57e39f17bcb531ff2933374e50f96c97781f8b0","target":"record","created_at":"2026-07-05T10:02:29Z","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":"d91b13ee6393b7dbd69a8f0fa853f6fe022c35d9a90706bfc0a5a69e4defb766","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T21:05:09Z","title_canon_sha256":"0a50b3eaffff2a61577335de7af892635ae633d78848a1bf0b5a59ae65a10da0"},"schema_version":"1.0","source":{"id":"2501.10555","kind":"arxiv","version":1}},"canonical_sha256":"d2505a41b1ffa03d1b8b6d08ac0cdb3d0eac636bbe18edb55f85f88813766950","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2505a41b1ffa03d1b8b6d08ac0cdb3d0eac636bbe18edb55f85f88813766950","first_computed_at":"2026-07-05T10:02:29.808801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:29.808801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MZt0WrRUNvLs/jaRpqVc+a61wfDgx4Bz9A035HKBpqV/RqglNpQULmDhA5qHtrfgijwq8FPtRr7ePhT1i+wADw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:29.809285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.10555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:365602343cba78b621b64b8ec57e39f17bcb531ff2933374e50f96c97781f8b0","sha256:764797f209b14442cd01fa1f15e6fe24f396a9ff6e2b777061ac56a7ba9c44f3"],"state_sha256":"6a4f8484280295a7fdb59d7a45e76654278ca90473ef92a16322351852d7a088"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H9AC7qf/Ie8FQ6GDfZ39MgZxymXG0eGDmpWaNatRTf7GOrkiBq+4rOVt/bhb3kunhH57lvqMjjZ1UdfBNFOxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:36:01.455488Z","bundle_sha256":"ca58d463d0dc74d00784fcd4ef506a28ef2596466f73f460d0ec7d4d051e7b4c"}}