{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XRGHKCEYGMTDOH3PRSXQ5MES4Q","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":"beb76e9d89b1760ef7ca5dacdc9b7528c387b3c4015d48c7ac8c1880f30ccf52","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-30T23:28:43Z","title_canon_sha256":"951a1d42efbca15feadd01789803e3e0e9c61df523cb41686f8e52ccfd150a5b"},"schema_version":"1.0","source":{"id":"2308.16361","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16361","created_at":"2026-07-05T09:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16361v2","created_at":"2026-07-05T09:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16361","created_at":"2026-07-05T09:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"XRGHKCEYGMTD","created_at":"2026-07-05T09:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"XRGHKCEYGMTDOH3P","created_at":"2026-07-05T09:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"XRGHKCEY","created_at":"2026-07-05T09:26:21Z"}],"graph_snapshots":[{"event_id":"sha256:5f21cbc5f19a8fd951be7bf49ea9860dc6617e7bb6742e03109740080eb2057a","target":"graph","created_at":"2026-07-05T09:26:21Z","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/2308.16361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), typified by OpenAI's GPT, have marked a significant advancement in artificial intelligence. Trained on vast amounts of text data, LLMs are capable of understanding and generating human-like text across a diverse range of topics. This study expands on the applications of LLMs, exploring their potential in data preprocessing, a critical stage in data mining and analytics applications. Aiming at tabular data, we delve into the applicability of state-of-the-art LLMs such as GPT-4 and GPT-4o for a series of preprocessing tasks, including error detection, data imputatio","authors_text":"Chuan Xiao, Haochen Zhang, Masafumi Oyamada, Yuyang Dong","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-30T23:28:43Z","title":"Large Language Models as Data Preprocessors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16361","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":"sha256:43e62f608ab890b619f4c08fc79d04fc1d99c8d7b4ea341c39bb8baee49c0b36","target":"record","created_at":"2026-07-05T09:26:21Z","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":"beb76e9d89b1760ef7ca5dacdc9b7528c387b3c4015d48c7ac8c1880f30ccf52","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-30T23:28:43Z","title_canon_sha256":"951a1d42efbca15feadd01789803e3e0e9c61df523cb41686f8e52ccfd150a5b"},"schema_version":"1.0","source":{"id":"2308.16361","kind":"arxiv","version":2}},"canonical_sha256":"bc4c7508983326371f6f8caf0eb092e40dc353415aa190f3a9d51ce75006ac12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc4c7508983326371f6f8caf0eb092e40dc353415aa190f3a9d51ce75006ac12","first_computed_at":"2026-07-05T09:26:21.834602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:21.834602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zhO8tnK/6pyR+m9vYGRmcYDtrHFoc7qG/NSPcoiedizWFNMOUS7NPOQSCnzVC76etrruOAcnuzhq/OKQHxrGAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:21.835109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.16361","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43e62f608ab890b619f4c08fc79d04fc1d99c8d7b4ea341c39bb8baee49c0b36","sha256:5f21cbc5f19a8fd951be7bf49ea9860dc6617e7bb6742e03109740080eb2057a"],"state_sha256":"399762e1e6b3ae224aa3b64fe51ce6e939057cfec77a439e04c1717218a2a9d3"}