{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z3LBORFPWO7S3XKM2SB5C3WZFB","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":"5222b2d97be7a287376f603c0b440477f1bec98d8f4afa4af9d3a9a8304ef759","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-02-09T15:37:39Z","title_canon_sha256":"d1c024083c619518b8ae453a168b797991835e8033fe276b78ab6d580c6d760f"},"schema_version":"1.0","source":{"id":"2302.04702","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04702","created_at":"2026-07-05T05:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04702v1","created_at":"2026-07-05T05:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04702","created_at":"2026-07-05T05:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"Z3LBORFPWO7S","created_at":"2026-07-05T05:40:17Z"},{"alias_kind":"pith_short_16","alias_value":"Z3LBORFPWO7S3XKM","created_at":"2026-07-05T05:40:17Z"},{"alias_kind":"pith_short_8","alias_value":"Z3LBORFP","created_at":"2026-07-05T05:40:17Z"}],"graph_snapshots":[{"event_id":"sha256:3726d2f228cfdc8162bfc4e6ce1740689e9f788450f0dde9f5c976f2bfa2fcec","target":"graph","created_at":"2026-07-05T05:40:17Z","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/2302.04702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Nowadays, machine learning (ML) plays a vital role in many aspects of our daily life. In essence, building well-performing ML applications requires the provision of high-quality data throughout the entire life-cycle of such applications. Nevertheless, most of the real-world tabular data suffer from different types of discrepancies, such as missing values, outliers, duplicates, pattern violation, and inconsistencies. Such discrepancies typically emerge while collecting, transferring, storing, and/or integrating the data. To deal with these discrepancies, numerous data cleaning methods have been","authors_text":"Christian Hammacher, Harald Schoening, Mohamed Abdelaal","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-02-09T15:37:39Z","title":"REIN: A Comprehensive Benchmark Framework for Data Cleaning Methods in ML Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04702","kind":"arxiv","version":1},"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:bc07d97f8a780639ad082e92f0e353b9dfcce4cebb3cc0bcb6454aa66ad568b4","target":"record","created_at":"2026-07-05T05:40:17Z","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":"5222b2d97be7a287376f603c0b440477f1bec98d8f4afa4af9d3a9a8304ef759","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-02-09T15:37:39Z","title_canon_sha256":"d1c024083c619518b8ae453a168b797991835e8033fe276b78ab6d580c6d760f"},"schema_version":"1.0","source":{"id":"2302.04702","kind":"arxiv","version":1}},"canonical_sha256":"ced61744afb3bf2ddd4cd483d16ed928532cdbb7f4b4368f246f27398625d4a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ced61744afb3bf2ddd4cd483d16ed928532cdbb7f4b4368f246f27398625d4a2","first_computed_at":"2026-07-05T05:40:17.583546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:17.583546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2X268WZfa5GPujtuxiumLdm1pbe3zqyxXKaKwUqa1KJa9yXR8OGkM9Y/eOnnBlrlLW7T7qtEwoS7RbBUwBS6Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:17.583916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.04702","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc07d97f8a780639ad082e92f0e353b9dfcce4cebb3cc0bcb6454aa66ad568b4","sha256:3726d2f228cfdc8162bfc4e6ce1740689e9f788450f0dde9f5c976f2bfa2fcec"],"state_sha256":"9dc9d49f7d2996d611a83422ee1f08640869e651caba96fb3333047fc1b53ff4"}