{"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"}