{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:K7EW3MR62A5D5BJSC4DKOWRSA3","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":"37873bb1a4f91a10b16a96fabf17d9b1168971939e2045e95b67df3c8d251983","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-09-15T07:19:03Z","title_canon_sha256":"a3d942cc82132d4869468d31862c622b6fdebbb8217bee5803021a32ee8d67f6"},"schema_version":"1.0","source":{"id":"2109.07127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.07127","created_at":"2026-07-05T03:14:46Z"},{"alias_kind":"arxiv_version","alias_value":"2109.07127v1","created_at":"2026-07-05T03:14:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07127","created_at":"2026-07-05T03:14:46Z"},{"alias_kind":"pith_short_12","alias_value":"K7EW3MR62A5D","created_at":"2026-07-05T03:14:46Z"},{"alias_kind":"pith_short_16","alias_value":"K7EW3MR62A5D5BJS","created_at":"2026-07-05T03:14:46Z"},{"alias_kind":"pith_short_8","alias_value":"K7EW3MR6","created_at":"2026-07-05T03:14:46Z"}],"graph_snapshots":[{"event_id":"sha256:dc9318c993d07fdf8cf65aab5eb50b38ad8d97f7f81d82653b3f8ab0daca7273","target":"graph","created_at":"2026-07-05T03:14:46Z","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/2109.07127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data cleaning is the initial stage of any machine learning project and is one of the most critical processes in data analysis. It is a critical step in ensuring that the dataset is devoid of incorrect or erroneous data. It can be done manually with data wrangling tools, or it can be completed automatically with a computer program. Data cleaning entails a slew of procedures that, once done, make the data ready for analysis. Given its significance in numerous fields, there is a growing interest in the development of efficient and effective data cleaning frameworks. In this survey, some of the mo","authors_text":"Arash Termehchy, Bakhtiyar Doskenov, Ga Young Lee, Lubna Alzamil","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-09-15T07:19:03Z","title":"A Survey on Data Cleaning Methods for Improved Machine Learning Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07127","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":"sha256:4b496361adf832b20797c3441aaae1c08074df5192bc0cf1896a1684d49dc262","target":"record","created_at":"2026-07-05T03:14:46Z","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":"37873bb1a4f91a10b16a96fabf17d9b1168971939e2045e95b67df3c8d251983","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-09-15T07:19:03Z","title_canon_sha256":"a3d942cc82132d4869468d31862c622b6fdebbb8217bee5803021a32ee8d67f6"},"schema_version":"1.0","source":{"id":"2109.07127","kind":"arxiv","version":1}},"canonical_sha256":"57c96db23ed03a3e85321706a75a3206dc5353ade7e996bed47d0649a203b600","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57c96db23ed03a3e85321706a75a3206dc5353ade7e996bed47d0649a203b600","first_computed_at":"2026-07-05T03:14:46.871112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:14:46.871112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqG8eP+5u+EC4W9UnW4+CrQes5xTssqc2EynLY0WospauSMs28aK9O5lQee9YvbE7r2DjpKC1Puz6XPVb/lGDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:14:46.871555Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.07127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b496361adf832b20797c3441aaae1c08074df5192bc0cf1896a1684d49dc262","sha256:dc9318c993d07fdf8cf65aab5eb50b38ad8d97f7f81d82653b3f8ab0daca7273"],"state_sha256":"5f9d13e8ac33e5b2c7f37d9605020b80ee8ba816ffcebf9e9505d7d3bcb46541"}