{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PQ2TJC3B6X4PR4QFMTQT7KZNKF","short_pith_number":"pith:PQ2TJC3B","schema_version":"1.0","canonical_sha256":"7c35348b61f5f8f8f20564e13fab2d5175eebb5b5b5f99d32cc53452d9216948","source":{"kind":"arxiv","id":"2207.14529","version":6},"attestation_state":"computed","paper":{"title":"The Effects of Data Quality on Machine Learning Performance on Tabular Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrea Nathansen, Felix Naumann, Hazar Harmouch, Hendrik Patzlaff, Lukas Budach, Moritz Feuerpfeil, Nele Noack, Nina Ihde, Sedir Mohammed","submitted_at":"2022-07-29T07:53:31Z","abstract_excerpt":"Modern artificial intelligence (AI) applications require large quantities of training and test data. This need creates critical challenges not only concerning the availability of such data, but also regarding its quality. For example, incomplete, erroneous, or inappropriate training data can lead to unreliable models that produce ultimately poor decisions. Trustworthy AI applications require high-quality training and test data along many quality dimensions, such as accuracy, completeness, and consistency.\n  We explore empirically the relationship between six data quality dimensions and the per"},"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":"2207.14529","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2022-07-29T07:53:31Z","cross_cats_sorted":[],"title_canon_sha256":"69dbf0f4bd7578aea4e131030b330798b13af13a348727349423030b7cca98ad","abstract_canon_sha256":"77cb1a5ac754073d0d35be69b3c741f5587a8fd70c9f85cc29c8a2f8a6d205e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:37.028361Z","signature_b64":"7BCPxfZxu9He2n7/mxEg+sl3oO8CoPLrENLjWIMy9FeeYilzZ2AUtGVkZNgGx0xm646j8y2Cf04F9uHp9mnuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c35348b61f5f8f8f20564e13fab2d5175eebb5b5b5f99d32cc53452d9216948","last_reissued_at":"2026-07-05T11:02:37.027824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:37.027824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Effects of Data Quality on Machine Learning Performance on Tabular Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrea Nathansen, Felix Naumann, Hazar Harmouch, Hendrik Patzlaff, Lukas Budach, Moritz Feuerpfeil, Nele Noack, Nina Ihde, Sedir Mohammed","submitted_at":"2022-07-29T07:53:31Z","abstract_excerpt":"Modern artificial intelligence (AI) applications require large quantities of training and test data. This need creates critical challenges not only concerning the availability of such data, but also regarding its quality. For example, incomplete, erroneous, or inappropriate training data can lead to unreliable models that produce ultimately poor decisions. Trustworthy AI applications require high-quality training and test data along many quality dimensions, such as accuracy, completeness, and consistency.\n  We explore empirically the relationship between six data quality dimensions and the per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.14529","kind":"arxiv","version":6},"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/2207.14529/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":"2207.14529","created_at":"2026-07-05T11:02:37.027888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.14529v6","created_at":"2026-07-05T11:02:37.027888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.14529","created_at":"2026-07-05T11:02:37.027888+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQ2TJC3B6X4P","created_at":"2026-07-05T11:02:37.027888+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQ2TJC3B6X4PR4QF","created_at":"2026-07-05T11:02:37.027888+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQ2TJC3B","created_at":"2026-07-05T11:02:37.027888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.21931","citing_title":"Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQ2TJC3B6X4PR4QFMTQT7KZNKF","json":"https://pith.science/pith/PQ2TJC3B6X4PR4QFMTQT7KZNKF.json","graph_json":"https://pith.science/api/pith-number/PQ2TJC3B6X4PR4QFMTQT7KZNKF/graph.json","events_json":"https://pith.science/api/pith-number/PQ2TJC3B6X4PR4QFMTQT7KZNKF/events.json","paper":"https://pith.science/paper/PQ2TJC3B"},"agent_actions":{"view_html":"https://pith.science/pith/PQ2TJC3B6X4PR4QFMTQT7KZNKF","download_json":"https://pith.science/pith/PQ2TJC3B6X4PR4QFMTQT7KZNKF.json","view_paper":"https://pith.science/paper/PQ2TJC3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.14529&json=true","fetch_graph":"https://pith.science/api/pith-number/PQ2TJC3B6X4PR4QFMTQT7KZNKF/graph.json","fetch_events":"https://pith.science/api/pith-number/PQ2TJC3B6X4PR4QFMTQT7KZNKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQ2TJC3B6X4PR4QFMTQT7KZNKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQ2TJC3B6X4PR4QFMTQT7KZNKF/action/storage_attestation","attest_author":"https://pith.science/pith/PQ2TJC3B6X4PR4QFMTQT7KZNKF/action/author_attestation","sign_citation":"https://pith.science/pith/PQ2TJC3B6X4PR4QFMTQT7KZNKF/action/citation_signature","submit_replication":"https://pith.science/pith/PQ2TJC3B6X4PR4QFMTQT7KZNKF/action/replication_record"}},"created_at":"2026-07-05T11:02:37.027888+00:00","updated_at":"2026-07-05T11:02:37.027888+00:00"}