{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FZXDSYR2HEYPMURJAZNQBIKT4B","short_pith_number":"pith:FZXDSYR2","schema_version":"1.0","canonical_sha256":"2e6e39623a3930f65229065b00a153e05433e37f5379edcae2743563951b476d","source":{"kind":"arxiv","id":"2310.01765","version":2},"attestation_state":"computed","paper":{"title":"Data Cleaning and Machine Learning: A Systematic Literature Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Amin Nikanjam, Dmytro Humeniuk, Foutse Khomh, Nafisa Ahmed, Pierre-Olivier C\\^ot\\'e","submitted_at":"2023-10-03T03:13:23Z","abstract_excerpt":"Context: Machine Learning (ML) is integrated into a growing number of systems for various applications. Because the performance of an ML model is highly dependent on the quality of the data it has been trained on, there is a growing interest in approaches to detect and repair data errors (i.e., data cleaning). Researchers are also exploring how ML can be used for data cleaning; hence creating a dual relationship between ML and data cleaning. To the best of our knowledge, there is no study that comprehensively reviews this relationship. Objective: This paper's objectives are twofold. First, it "},"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":"2310.01765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T03:13:23Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"3b0c2c821b5826e64047b2919b49b6553b703f9a9fefd7be639ad5096c0d8327","abstract_canon_sha256":"e4b8198db155e46b01944e9a5c49f75efb697eada34cb3a0f00a0c1d73ea2163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:28.955149Z","signature_b64":"CytR0w/VIIS873P99x4fiGGySobpHwGDRWehBYYgJ/57SE9o3h5h69MgoobGskAxElBCUqcxpT2uyczIbWnhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6e39623a3930f65229065b00a153e05433e37f5379edcae2743563951b476d","last_reissued_at":"2026-07-05T08:25:28.954676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:28.954676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Cleaning and Machine Learning: A Systematic Literature Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Amin Nikanjam, Dmytro Humeniuk, Foutse Khomh, Nafisa Ahmed, Pierre-Olivier C\\^ot\\'e","submitted_at":"2023-10-03T03:13:23Z","abstract_excerpt":"Context: Machine Learning (ML) is integrated into a growing number of systems for various applications. Because the performance of an ML model is highly dependent on the quality of the data it has been trained on, there is a growing interest in approaches to detect and repair data errors (i.e., data cleaning). Researchers are also exploring how ML can be used for data cleaning; hence creating a dual relationship between ML and data cleaning. To the best of our knowledge, there is no study that comprehensively reviews this relationship. Objective: This paper's objectives are twofold. First, it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01765","kind":"arxiv","version":2},"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/2310.01765/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":"2310.01765","created_at":"2026-07-05T08:25:28.954732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01765v2","created_at":"2026-07-05T08:25:28.954732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01765","created_at":"2026-07-05T08:25:28.954732+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZXDSYR2HEYP","created_at":"2026-07-05T08:25:28.954732+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZXDSYR2HEYPMURJ","created_at":"2026-07-05T08:25:28.954732+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZXDSYR2","created_at":"2026-07-05T08:25:28.954732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B","json":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B.json","graph_json":"https://pith.science/api/pith-number/FZXDSYR2HEYPMURJAZNQBIKT4B/graph.json","events_json":"https://pith.science/api/pith-number/FZXDSYR2HEYPMURJAZNQBIKT4B/events.json","paper":"https://pith.science/paper/FZXDSYR2"},"agent_actions":{"view_html":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B","download_json":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B.json","view_paper":"https://pith.science/paper/FZXDSYR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01765&json=true","fetch_graph":"https://pith.science/api/pith-number/FZXDSYR2HEYPMURJAZNQBIKT4B/graph.json","fetch_events":"https://pith.science/api/pith-number/FZXDSYR2HEYPMURJAZNQBIKT4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/action/storage_attestation","attest_author":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/action/author_attestation","sign_citation":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/action/citation_signature","submit_replication":"https://pith.science/pith/FZXDSYR2HEYPMURJAZNQBIKT4B/action/replication_record"}},"created_at":"2026-07-05T08:25:28.954732+00:00","updated_at":"2026-07-05T08:25:28.954732+00:00"}