{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IEJTJ6GWQF5L3DRBQSL4ARXPPX","short_pith_number":"pith:IEJTJ6GW","canonical_record":{"source":{"id":"2502.08828","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T22:34:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f7203f0afb655d1c9670e415e1b3423cd38803b874821d35761da3b4a146c8d","abstract_canon_sha256":"e25ac639e0d4da839457ccc5f00ca85c95dd45758ee3d211e2f68b8ff8a498b7"},"schema_version":"1.0"},"canonical_sha256":"411334f8d6817abd8e218497c046ef7dd91c1c25f7bbab8457e61efe95e7f0c8","source":{"kind":"arxiv","id":"2502.08828","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08828","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08828v2","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08828","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_12","alias_value":"IEJTJ6GWQF5L","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_16","alias_value":"IEJTJ6GWQF5L3DRB","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_8","alias_value":"IEJTJ6GW","created_at":"2026-07-05T10:14:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IEJTJ6GWQF5L3DRBQSL4ARXPPX","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08828","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T22:34:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f7203f0afb655d1c9670e415e1b3423cd38803b874821d35761da3b4a146c8d","abstract_canon_sha256":"e25ac639e0d4da839457ccc5f00ca85c95dd45758ee3d211e2f68b8ff8a498b7"},"schema_version":"1.0"},"canonical_sha256":"411334f8d6817abd8e218497c046ef7dd91c1c25f7bbab8457e61efe95e7f0c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:51.431866Z","signature_b64":"p87UXwFufKNE/drsPFNCeYFpKyM59aIWWHKDAiX3Vnoex8sXNqSlBgDuM6mWAtXg2Q5VDhyPbvf9eOLwTNngDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"411334f8d6817abd8e218497c046ef7dd91c1c25f7bbab8457e61efe95e7f0c8","last_reissued_at":"2026-07-05T10:14:51.431383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:51.431383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08828","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:14:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eXllsVujgbei0lcGVoUTbZfEWaI0mm9syECYnSBqyiUUQQO9cHsEkvjxqAxMn/ub20/tsZ2WGozIpD8jRW+bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:59:15.939951Z"},"content_sha256":"70014ee2053e46fd1da50ef29b4ad0991f3153f6d3071f4cc103a567200b604c","schema_version":"1.0","event_id":"sha256:70014ee2053e46fd1da50ef29b4ad0991f3153f6d3071f4cc103a567200b604c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IEJTJ6GWQF5L3DRBQSL4ARXPPX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Data-Centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arun Vignesh Malarkkan, Cong Wei, Denghui Zhang, Dongjie Wang, Haoyue Bai, Nanxu Gong, Sixun Dong, Wangyang Ying, Xinyuan Wang, Yanjie Fu","submitted_at":"2025-02-12T22:34:50Z","abstract_excerpt":"Tabular data is one of the most widely used data formats across various domains such as bioinformatics, healthcare, and marketing. As artificial intelligence moves towards a data-centric perspective, improving data quality is essential for enhancing model performance in tabular data-driven applications. This survey focuses on data-driven tabular data optimization, specifically exploring reinforcement learning (RL) and generative approaches for feature selection and feature generation as fundamental techniques for refining data spaces. Feature selection aims to identify and retain the most info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08828","kind":"arxiv","version":2},"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/2502.08828/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":"2026-07-05T10:14:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1HHjvVHhuG//lgzOLWUBJHw+R1M1JBaiQCYG8ov7xbMdvjNZ71Ei6Ljm3NkDDr9rmrhRyWrZtRVvTFqmJkBDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:59:15.940487Z"},"content_sha256":"056461c4e2ccb9b48e4f6d819d1b3bf03ff8d752822d699ddc67f41cbe5f357c","schema_version":"1.0","event_id":"sha256:056461c4e2ccb9b48e4f6d819d1b3bf03ff8d752822d699ddc67f41cbe5f357c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEJTJ6GWQF5L3DRBQSL4ARXPPX/bundle.json","state_url":"https://pith.science/pith/IEJTJ6GWQF5L3DRBQSL4ARXPPX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEJTJ6GWQF5L3DRBQSL4ARXPPX/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":"2026-08-10T03:59:15Z","links":{"resolver":"https://pith.science/pith/IEJTJ6GWQF5L3DRBQSL4ARXPPX","bundle":"https://pith.science/pith/IEJTJ6GWQF5L3DRBQSL4ARXPPX/bundle.json","state":"https://pith.science/pith/IEJTJ6GWQF5L3DRBQSL4ARXPPX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEJTJ6GWQF5L3DRBQSL4ARXPPX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IEJTJ6GWQF5L3DRBQSL4ARXPPX","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":"e25ac639e0d4da839457ccc5f00ca85c95dd45758ee3d211e2f68b8ff8a498b7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T22:34:50Z","title_canon_sha256":"9f7203f0afb655d1c9670e415e1b3423cd38803b874821d35761da3b4a146c8d"},"schema_version":"1.0","source":{"id":"2502.08828","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08828","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08828v2","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08828","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_12","alias_value":"IEJTJ6GWQF5L","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_16","alias_value":"IEJTJ6GWQF5L3DRB","created_at":"2026-07-05T10:14:51Z"},{"alias_kind":"pith_short_8","alias_value":"IEJTJ6GW","created_at":"2026-07-05T10:14:51Z"}],"graph_snapshots":[{"event_id":"sha256:056461c4e2ccb9b48e4f6d819d1b3bf03ff8d752822d699ddc67f41cbe5f357c","target":"graph","created_at":"2026-07-05T10:14:51Z","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/2502.08828/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 data formats across various domains such as bioinformatics, healthcare, and marketing. As artificial intelligence moves towards a data-centric perspective, improving data quality is essential for enhancing model performance in tabular data-driven applications. This survey focuses on data-driven tabular data optimization, specifically exploring reinforcement learning (RL) and generative approaches for feature selection and feature generation as fundamental techniques for refining data spaces. Feature selection aims to identify and retain the most info","authors_text":"Arun Vignesh Malarkkan, Cong Wei, Denghui Zhang, Dongjie Wang, Haoyue Bai, Nanxu Gong, Sixun Dong, Wangyang Ying, Xinyuan Wang, Yanjie Fu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T22:34:50Z","title":"A Survey on Data-Centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08828","kind":"arxiv","version":2},"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":"sha256:70014ee2053e46fd1da50ef29b4ad0991f3153f6d3071f4cc103a567200b604c","target":"record","created_at":"2026-07-05T10:14:51Z","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":"e25ac639e0d4da839457ccc5f00ca85c95dd45758ee3d211e2f68b8ff8a498b7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T22:34:50Z","title_canon_sha256":"9f7203f0afb655d1c9670e415e1b3423cd38803b874821d35761da3b4a146c8d"},"schema_version":"1.0","source":{"id":"2502.08828","kind":"arxiv","version":2}},"canonical_sha256":"411334f8d6817abd8e218497c046ef7dd91c1c25f7bbab8457e61efe95e7f0c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"411334f8d6817abd8e218497c046ef7dd91c1c25f7bbab8457e61efe95e7f0c8","first_computed_at":"2026-07-05T10:14:51.431383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:51.431383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p87UXwFufKNE/drsPFNCeYFpKyM59aIWWHKDAiX3Vnoex8sXNqSlBgDuM6mWAtXg2Q5VDhyPbvf9eOLwTNngDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:51.431866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08828","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70014ee2053e46fd1da50ef29b4ad0991f3153f6d3071f4cc103a567200b604c","sha256:056461c4e2ccb9b48e4f6d819d1b3bf03ff8d752822d699ddc67f41cbe5f357c"],"state_sha256":"784151ce207fc8b05caaf97516c911e12beceaa16b681f10dc33e5fe799c8a53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"og4uxmmCNgfJUuhpIJoF5/ItaQr7SsOZKE+sELibXvw3p3NDpOe4ggBIqXezuG8TmFzzkuR8X4KXTKkJr+dNDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:59:15.945610Z","bundle_sha256":"d9b3f4bb0c8b7b81ddea9ab55b71b680a43730da06ba37a7bdab1bc8249c1c71"}}