{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XRGHKCEYGMTDOH3PRSXQ5MES4Q","short_pith_number":"pith:XRGHKCEY","schema_version":"1.0","canonical_sha256":"bc4c7508983326371f6f8caf0eb092e40dc353415aa190f3a9d51ce75006ac12","source":{"kind":"arxiv","id":"2308.16361","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models as Data Preprocessors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Chuan Xiao, Haochen Zhang, Masafumi Oyamada, Yuyang Dong","submitted_at":"2023-08-30T23:28:43Z","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"},"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":"2308.16361","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-30T23:28:43Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"951a1d42efbca15feadd01789803e3e0e9c61df523cb41686f8e52ccfd150a5b","abstract_canon_sha256":"beb76e9d89b1760ef7ca5dacdc9b7528c387b3c4015d48c7ac8c1880f30ccf52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:21.835109Z","signature_b64":"zhO8tnK/6pyR+m9vYGRmcYDtrHFoc7qG/NSPcoiedizWFNMOUS7NPOQSCnzVC76etrruOAcnuzhq/OKQHxrGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc4c7508983326371f6f8caf0eb092e40dc353415aa190f3a9d51ce75006ac12","last_reissued_at":"2026-07-05T09:26:21.834602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:21.834602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Data Preprocessors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Chuan Xiao, Haochen Zhang, Masafumi Oyamada, Yuyang Dong","submitted_at":"2023-08-30T23:28:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16361","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/2308.16361/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":"2308.16361","created_at":"2026-07-05T09:26:21.834660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16361v2","created_at":"2026-07-05T09:26:21.834660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16361","created_at":"2026-07-05T09:26:21.834660+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRGHKCEYGMTD","created_at":"2026-07-05T09:26:21.834660+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRGHKCEYGMTDOH3P","created_at":"2026-07-05T09:26:21.834660+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRGHKCEY","created_at":"2026-07-05T09:26:21.834660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25388","citing_title":"TabClean: Reusable LLM-Synthesized Programs for Tabular Data Cleaning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24679","citing_title":"FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25814","citing_title":"Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13766","citing_title":"A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards","ref_index":219,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q","json":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q.json","graph_json":"https://pith.science/api/pith-number/XRGHKCEYGMTDOH3PRSXQ5MES4Q/graph.json","events_json":"https://pith.science/api/pith-number/XRGHKCEYGMTDOH3PRSXQ5MES4Q/events.json","paper":"https://pith.science/paper/XRGHKCEY"},"agent_actions":{"view_html":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q","download_json":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q.json","view_paper":"https://pith.science/paper/XRGHKCEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16361&json=true","fetch_graph":"https://pith.science/api/pith-number/XRGHKCEYGMTDOH3PRSXQ5MES4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/XRGHKCEYGMTDOH3PRSXQ5MES4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/action/storage_attestation","attest_author":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/action/author_attestation","sign_citation":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/action/citation_signature","submit_replication":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/action/replication_record"}},"created_at":"2026-07-05T09:26:21.834660+00:00","updated_at":"2026-07-05T09:26:21.834660+00:00"}