{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XRGHKCEYGMTDOH3PRSXQ5MES4Q","short_pith_number":"pith:XRGHKCEY","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"},"canonical_sha256":"bc4c7508983326371f6f8caf0eb092e40dc353415aa190f3a9d51ce75006ac12","source":{"kind":"arxiv","id":"2308.16361","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XRGHKCEYGMTDOH3PRSXQ5MES4Q","target":"record","payload":{"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"},"canonical_sha256":"bc4c7508983326371f6f8caf0eb092e40dc353415aa190f3a9d51ce75006ac12","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"},"source_kind":"arxiv","source_id":"2308.16361","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":"2026-07-05T09:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VlxpjfKKDGbzYeEN9axY93Gv528U4eK3D9lTkrmOaIA6uw/Nv/JuE5FXeUHKhrvEltF0I63EU/e4LJfcy7RuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:03:58.426650Z"},"content_sha256":"43e62f608ab890b619f4c08fc79d04fc1d99c8d7b4ea341c39bb8baee49c0b36","schema_version":"1.0","event_id":"sha256:43e62f608ab890b619f4c08fc79d04fc1d99c8d7b4ea341c39bb8baee49c0b36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XRGHKCEYGMTDOH3PRSXQ5MES4Q","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QaLTalriM5wyams0x91PNiJELxKOx5Lt7zY7N4kNQkhUDKvTlOqJj+1qAKALeXBmYDaxZ+8Ri4ZY0tYRtwnZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:03:58.427167Z"},"content_sha256":"5f21cbc5f19a8fd951be7bf49ea9860dc6617e7bb6742e03109740080eb2057a","schema_version":"1.0","event_id":"sha256:5f21cbc5f19a8fd951be7bf49ea9860dc6617e7bb6742e03109740080eb2057a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/bundle.json","state_url":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/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":"2026-08-09T13:03:58Z","links":{"resolver":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q","bundle":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/bundle.json","state":"https://pith.science/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XRGHKCEYGMTDOH3PRSXQ5MES4Q/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FGDog3sW0HHkgdySUwTv5NccBh+HkG71WuyeqiDZABBpgezzBE9EAKbQt+8ta0+O+VqIq6cL2sngu8ax69nZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:03:58.430572Z","bundle_sha256":"14b080b2eb2f3ddd63bf9f8180ac256eef089325c6611321d6a4b3f2302bb6e3"}}