{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z3LBORFPWO7S3XKM2SB5C3WZFB","short_pith_number":"pith:Z3LBORFP","schema_version":"1.0","canonical_sha256":"ced61744afb3bf2ddd4cd483d16ed928532cdbb7f4b4368f246f27398625d4a2","source":{"kind":"arxiv","id":"2302.04702","version":1},"attestation_state":"computed","paper":{"title":"REIN: A Comprehensive Benchmark Framework for Data Cleaning Methods in ML Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Christian Hammacher, Harald Schoening, Mohamed Abdelaal","submitted_at":"2023-02-09T15:37:39Z","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"},"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":"2302.04702","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-02-09T15:37:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d1c024083c619518b8ae453a168b797991835e8033fe276b78ab6d580c6d760f","abstract_canon_sha256":"5222b2d97be7a287376f603c0b440477f1bec98d8f4afa4af9d3a9a8304ef759"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:17.583916Z","signature_b64":"2X268WZfa5GPujtuxiumLdm1pbe3zqyxXKaKwUqa1KJa9yXR8OGkM9Y/eOnnBlrlLW7T7qtEwoS7RbBUwBS6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ced61744afb3bf2ddd4cd483d16ed928532cdbb7f4b4368f246f27398625d4a2","last_reissued_at":"2026-07-05T05:40:17.583546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:17.583546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REIN: A Comprehensive Benchmark Framework for Data Cleaning Methods in ML Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Christian Hammacher, Harald Schoening, Mohamed Abdelaal","submitted_at":"2023-02-09T15:37:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04702","kind":"arxiv","version":1},"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/2302.04702/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":"2302.04702","created_at":"2026-07-05T05:40:17.583600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04702v1","created_at":"2026-07-05T05:40:17.583600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04702","created_at":"2026-07-05T05:40:17.583600+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3LBORFPWO7S","created_at":"2026-07-05T05:40:17.583600+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3LBORFPWO7S3XKM","created_at":"2026-07-05T05:40:17.583600+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3LBORFP","created_at":"2026-07-05T05:40:17.583600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20881","citing_title":"Understanding and evaluating computer vision models through the lens of counterfactuals","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z3LBORFPWO7S3XKM2SB5C3WZFB","json":"https://pith.science/pith/Z3LBORFPWO7S3XKM2SB5C3WZFB.json","graph_json":"https://pith.science/api/pith-number/Z3LBORFPWO7S3XKM2SB5C3WZFB/graph.json","events_json":"https://pith.science/api/pith-number/Z3LBORFPWO7S3XKM2SB5C3WZFB/events.json","paper":"https://pith.science/paper/Z3LBORFP"},"agent_actions":{"view_html":"https://pith.science/pith/Z3LBORFPWO7S3XKM2SB5C3WZFB","download_json":"https://pith.science/pith/Z3LBORFPWO7S3XKM2SB5C3WZFB.json","view_paper":"https://pith.science/paper/Z3LBORFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04702&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3LBORFPWO7S3XKM2SB5C3WZFB/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3LBORFPWO7S3XKM2SB5C3WZFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3LBORFPWO7S3XKM2SB5C3WZFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3LBORFPWO7S3XKM2SB5C3WZFB/action/storage_attestation","attest_author":"https://pith.science/pith/Z3LBORFPWO7S3XKM2SB5C3WZFB/action/author_attestation","sign_citation":"https://pith.science/pith/Z3LBORFPWO7S3XKM2SB5C3WZFB/action/citation_signature","submit_replication":"https://pith.science/pith/Z3LBORFPWO7S3XKM2SB5C3WZFB/action/replication_record"}},"created_at":"2026-07-05T05:40:17.583600+00:00","updated_at":"2026-07-05T05:40:17.583600+00:00"}