{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ACJRXITYT42IMNYFGH5ZIPUAJ7","short_pith_number":"pith:ACJRXITY","canonical_record":{"source":{"id":"2412.06724","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-12-09T18:13:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9294a33175fa0c2a5a901a59a678b0c146a06dc272dce0f19ba875710a793fe","abstract_canon_sha256":"e67da387e3a8ccb31160d087a930d1d34b8add1ec554f9c749ff55ea3cb9fa00"},"schema_version":"1.0"},"canonical_sha256":"00931ba2789f3486370531fb943e804fd8e45fd103d8b604c1a4ef51ca30b56f","source":{"kind":"arxiv","id":"2412.06724","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06724","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06724v3","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06724","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"pith_short_12","alias_value":"ACJRXITYT42I","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"pith_short_16","alias_value":"ACJRXITYT42IMNYF","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"pith_short_8","alias_value":"ACJRXITY","created_at":"2026-07-05T11:57:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ACJRXITYT42IMNYFGH5ZIPUAJ7","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06724","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-12-09T18:13:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9294a33175fa0c2a5a901a59a678b0c146a06dc272dce0f19ba875710a793fe","abstract_canon_sha256":"e67da387e3a8ccb31160d087a930d1d34b8add1ec554f9c749ff55ea3cb9fa00"},"schema_version":"1.0"},"canonical_sha256":"00931ba2789f3486370531fb943e804fd8e45fd103d8b604c1a4ef51ca30b56f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:53.908889Z","signature_b64":"eyc9nSpy7E92NSEi0V7z2lKtnmDTatsiz4VCL5i1Aut3P8VptCS+qwDlzrNRVEHJMCaSEqUv2WAicsxrCbilDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00931ba2789f3486370531fb943e804fd8e45fd103d8b604c1a4ef51ca30b56f","last_reissued_at":"2026-07-05T11:57:53.908397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:53.908397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06724","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:57:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AK+khLNYvx0OECBoA0bJ3V8Pn0qZ7wOs7VXpxpfuk8WFJnrgKbjKwhoqr1P07JdfewQ1gujvARkGvGoeHJ+6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T16:22:48.250816Z"},"content_sha256":"02c1402999a603d2c1b31dde8eadd2491249f2b11a9100d79977f51751d4d714","schema_version":"1.0","event_id":"sha256:02c1402999a603d2c1b31dde8eadd2491249f2b11a9100d79977f51751d4d714"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ACJRXITYT42IMNYFGH5ZIPUAJ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"Bertram Lud\\\"ascher, Lan Li, Liri Fang, Vetle I. Torvik","submitted_at":"2024-12-09T18:13:27Z","abstract_excerpt":"Data cleaning is a time-consuming and error-prone manual process, even with modern workflow tools such as OpenRefine. We present AutoDCWorkflow, an LLM-based pipeline for automatically generating data-cleaning workflows. The pipeline takes a raw table and a data analysis purpose, and generates a sequence of OpenRefine operations designed to produce a minimal, clean table sufficient to address the purpose. Six operations correspond to common data quality issues, including format inconsistencies, type errors, and duplicates.\n  To evaluate AutoDCWorkflow, we create a benchmark with metrics assess"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06724","kind":"arxiv","version":3},"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/2412.06724/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":"2026-07-05T11:57:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8r5WL/IyN89aTxs0wF+0vq1eK5mMWJ+rAIh++yFNJuvI095HgTObnQkGv2rdPfZd0M9UnV56ICuimowSG123Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T16:22:48.251192Z"},"content_sha256":"b12c6e3d6ed38db9c8bbdf0ddd39eed5acd13f470c844d618ead5e4a187e6c6d","schema_version":"1.0","event_id":"sha256:b12c6e3d6ed38db9c8bbdf0ddd39eed5acd13f470c844d618ead5e4a187e6c6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/bundle.json","state_url":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/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":"2026-07-26T16:22:48Z","links":{"resolver":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7","bundle":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/bundle.json","state":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ACJRXITYT42IMNYFGH5ZIPUAJ7","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":"e67da387e3a8ccb31160d087a930d1d34b8add1ec554f9c749ff55ea3cb9fa00","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-12-09T18:13:27Z","title_canon_sha256":"e9294a33175fa0c2a5a901a59a678b0c146a06dc272dce0f19ba875710a793fe"},"schema_version":"1.0","source":{"id":"2412.06724","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06724","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06724v3","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06724","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"pith_short_12","alias_value":"ACJRXITYT42I","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"pith_short_16","alias_value":"ACJRXITYT42IMNYF","created_at":"2026-07-05T11:57:53Z"},{"alias_kind":"pith_short_8","alias_value":"ACJRXITY","created_at":"2026-07-05T11:57:53Z"}],"graph_snapshots":[{"event_id":"sha256:b12c6e3d6ed38db9c8bbdf0ddd39eed5acd13f470c844d618ead5e4a187e6c6d","target":"graph","created_at":"2026-07-05T11:57:53Z","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/2412.06724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data cleaning is a time-consuming and error-prone manual process, even with modern workflow tools such as OpenRefine. We present AutoDCWorkflow, an LLM-based pipeline for automatically generating data-cleaning workflows. The pipeline takes a raw table and a data analysis purpose, and generates a sequence of OpenRefine operations designed to produce a minimal, clean table sufficient to address the purpose. Six operations correspond to common data quality issues, including format inconsistencies, type errors, and duplicates.\n  To evaluate AutoDCWorkflow, we create a benchmark with metrics assess","authors_text":"Bertram Lud\\\"ascher, Lan Li, Liri Fang, Vetle I. Torvik","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-12-09T18:13:27Z","title":"AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06724","kind":"arxiv","version":3},"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":"sha256:02c1402999a603d2c1b31dde8eadd2491249f2b11a9100d79977f51751d4d714","target":"record","created_at":"2026-07-05T11:57:53Z","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":"e67da387e3a8ccb31160d087a930d1d34b8add1ec554f9c749ff55ea3cb9fa00","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-12-09T18:13:27Z","title_canon_sha256":"e9294a33175fa0c2a5a901a59a678b0c146a06dc272dce0f19ba875710a793fe"},"schema_version":"1.0","source":{"id":"2412.06724","kind":"arxiv","version":3}},"canonical_sha256":"00931ba2789f3486370531fb943e804fd8e45fd103d8b604c1a4ef51ca30b56f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00931ba2789f3486370531fb943e804fd8e45fd103d8b604c1a4ef51ca30b56f","first_computed_at":"2026-07-05T11:57:53.908397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:53.908397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eyc9nSpy7E92NSEi0V7z2lKtnmDTatsiz4VCL5i1Aut3P8VptCS+qwDlzrNRVEHJMCaSEqUv2WAicsxrCbilDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:53.908889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06724","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02c1402999a603d2c1b31dde8eadd2491249f2b11a9100d79977f51751d4d714","sha256:b12c6e3d6ed38db9c8bbdf0ddd39eed5acd13f470c844d618ead5e4a187e6c6d"],"state_sha256":"363cd18981daea7cbb92aa46d4625f446b38ced58c2b41fb5ace570778f2a246"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SJOQHlHeT7bmSkzGWnSO2Cr92v49ii1qC2PhnFicfs12Qzu/Ue+YUTLBeuT8bIZGBKJOtacrCgKnoFzcafZPDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T16:22:48.253668Z","bundle_sha256":"01b189c2e5489fde059352c5bcf5c0cf3541578a5bacb748266b724fdd32a3cc"}}