{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ACJRXITYT42IMNYFGH5ZIPUAJ7","short_pith_number":"pith:ACJRXITY","schema_version":"1.0","canonical_sha256":"00931ba2789f3486370531fb943e804fd8e45fd103d8b604c1a4ef51ca30b56f","source":{"kind":"arxiv","id":"2412.06724","version":3},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.06724","created_at":"2026-07-05T11:57:53.908459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06724v3","created_at":"2026-07-05T11:57:53.908459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06724","created_at":"2026-07-05T11:57:53.908459+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACJRXITYT42I","created_at":"2026-07-05T11:57:53.908459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACJRXITYT42IMNYF","created_at":"2026-07-05T11:57:53.908459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACJRXITY","created_at":"2026-07-05T11:57:53.908459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07504","citing_title":"Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25388","citing_title":"TabClean: Reusable LLM-Synthesized Programs for Tabular Data Cleaning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12376","citing_title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21465","citing_title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12376","citing_title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7","json":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7.json","graph_json":"https://pith.science/api/pith-number/ACJRXITYT42IMNYFGH5ZIPUAJ7/graph.json","events_json":"https://pith.science/api/pith-number/ACJRXITYT42IMNYFGH5ZIPUAJ7/events.json","paper":"https://pith.science/paper/ACJRXITY"},"agent_actions":{"view_html":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7","download_json":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7.json","view_paper":"https://pith.science/paper/ACJRXITY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06724&json=true","fetch_graph":"https://pith.science/api/pith-number/ACJRXITYT42IMNYFGH5ZIPUAJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/ACJRXITYT42IMNYFGH5ZIPUAJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/action/storage_attestation","attest_author":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/action/author_attestation","sign_citation":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/action/citation_signature","submit_replication":"https://pith.science/pith/ACJRXITYT42IMNYFGH5ZIPUAJ7/action/replication_record"}},"created_at":"2026-07-05T11:57:53.908459+00:00","updated_at":"2026-07-05T11:57:53.908459+00:00"}