{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2JIFUQNR76QD2G4LNUEKYDG3HU","short_pith_number":"pith:2JIFUQNR","schema_version":"1.0","canonical_sha256":"d2505a41b1ffa03d1b8b6d08ac0cdb3d0eac636bbe18edb55f85f88813766950","source":{"kind":"arxiv","id":"2501.10555","version":1},"attestation_state":"computed","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 "},"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":"2501.10555","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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.10555","created_at":"2026-07-05T10:02:29.808866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10555v1","created_at":"2026-07-05T10:02:29.808866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10555","created_at":"2026-07-05T10:02:29.808866+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JIFUQNR76QD","created_at":"2026-07-05T10:02:29.808866+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JIFUQNR76QD2G4L","created_at":"2026-07-05T10:02:29.808866+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JIFUQNR","created_at":"2026-07-05T10:02:29.808866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24417","citing_title":"LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU","json":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU.json","graph_json":"https://pith.science/api/pith-number/2JIFUQNR76QD2G4LNUEKYDG3HU/graph.json","events_json":"https://pith.science/api/pith-number/2JIFUQNR76QD2G4LNUEKYDG3HU/events.json","paper":"https://pith.science/paper/2JIFUQNR"},"agent_actions":{"view_html":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU","download_json":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU.json","view_paper":"https://pith.science/paper/2JIFUQNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10555&json=true","fetch_graph":"https://pith.science/api/pith-number/2JIFUQNR76QD2G4LNUEKYDG3HU/graph.json","fetch_events":"https://pith.science/api/pith-number/2JIFUQNR76QD2G4LNUEKYDG3HU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/action/storage_attestation","attest_author":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/action/author_attestation","sign_citation":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/action/citation_signature","submit_replication":"https://pith.science/pith/2JIFUQNR76QD2G4LNUEKYDG3HU/action/replication_record"}},"created_at":"2026-07-05T10:02:29.808866+00:00","updated_at":"2026-07-05T10:02:29.808866+00:00"}