{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4KJIRZN3JJBU2Y6272MJSPMCMF","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":"3e81755e68be5803cb920d116150d194e94431a2ec59c71fa9109cbe086ed4ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-04-26T13:07:53Z","title_canon_sha256":"8a1f0abccd4d34ab1d5832c3085b3d2d8722e0be08d1acab9b63da87180bf015"},"schema_version":"1.0","source":{"id":"1904.11827","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11827","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11827v2","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11827","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"4KJIRZN3JJBU","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4KJIRZN3JJBU2Y62","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4KJIRZN3","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:70c97607c04452d7a795a046ab8de92963c1cbdb913869e64296760f09759eb8","target":"graph","created_at":"2026-05-17T23:46:52Z","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"},"paper":{"abstract_excerpt":"The analyst effort in data cleaning is gradually shifting away from the design of hand-written scripts to building and tuning complex pipelines of automated data cleaning libraries. Hyper-parameter tuning for data cleaning is very different than hyper-parameter tuning for machine learning since the pipeline components and objective functions have structure that tuning algorithms can exploit. This paper proposes a framework, called AlphaClean, that rethinks parameter tuning for data cleaning pipelines. AlphaClean provides users with a rich library to define data quality measures with weighted s","authors_text":"Eugene Wu, Sanjay Krishnan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-04-26T13:07:53Z","title":"AlphaClean: Automatic Generation of Data Cleaning Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11827","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:a8425952eb51ef2e3ecfa884a5a9c48c272166e8d77a1838b1b9789c6f561c54","target":"record","created_at":"2026-05-17T23:46:52Z","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":"3e81755e68be5803cb920d116150d194e94431a2ec59c71fa9109cbe086ed4ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-04-26T13:07:53Z","title_canon_sha256":"8a1f0abccd4d34ab1d5832c3085b3d2d8722e0be08d1acab9b63da87180bf015"},"schema_version":"1.0","source":{"id":"1904.11827","kind":"arxiv","version":2}},"canonical_sha256":"e29288e5bb4a434d63dafe98993d82614e19be172810a4b2c780241de82a293c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e29288e5bb4a434d63dafe98993d82614e19be172810a4b2c780241de82a293c","first_computed_at":"2026-05-17T23:46:52.329468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:52.329468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LhEdg6UtYDygnvEb3mhPVlf6Lxy4mE8HTwiX0TzNFK8OWekw6RnoAYeSmuu2aBnFgBA1gttai5GUfJ2let2JDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:52.330207Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.11827","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8425952eb51ef2e3ecfa884a5a9c48c272166e8d77a1838b1b9789c6f561c54","sha256:70c97607c04452d7a795a046ab8de92963c1cbdb913869e64296760f09759eb8"],"state_sha256":"ca1bd8422f6c458ab8df75cc82aa55ce4880cb54fc9e0da04d9b698ef2551cbb"}