{"id":"W4399174291","doi":"10.1145/3654963","title":"OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transport","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Universitas Brawijaya","keywords":"Computer science; Scalability; Mathematical optimization; Independence (probability theory); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001167637,0.0001375402,0.0001603445,0.0001084206,0.0001692001,0.000110118,0.0132617,0.00004329223,0.00001064247],"category_scores_gemma":[0.0002543516,0.0001161313,0.00005000392,0.0004773217,0.00007938879,0.002619752,0.008566443,0.0002184535,0.000002078208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002918773,"about_ca_system_score_gemma":0.00003941914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007751763,"about_ca_topic_score_gemma":4.667616e-7,"domain_scores_codex":[0.9981532,0.000006811773,0.0003433266,0.0006852566,0.0006174715,0.0001939547],"domain_scores_gemma":[0.9975135,0.0001325283,0.0002205271,0.002004114,0.00009990761,0.00002938809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009045592,0.0001823696,0.003155122,0.002264482,0.0006319392,0.000006737579,0.0005692481,0.04409605,0.001740423,0.9128144,0.008483176,0.02596556],"study_design_scores_gemma":[0.0002774451,0.00004344212,0.001948513,0.0005907605,0.0001625042,0.000005206388,0.0002626593,0.9804069,0.0003233357,0.0125913,0.003225197,0.0001627812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0236423,0.00007945192,0.971218,0.002276841,0.0003814142,0.0006422068,0.0005595881,0.0001413885,0.001058778],"genre_scores_gemma":[0.5674987,0.00001115843,0.4321807,0.00003499403,0.00006175147,0.000004349426,0.0001419916,0.00001346612,0.00005284139],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9363108,"threshold_uncertainty_score":0.9994521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1243438065986618,"score_gpt":0.3641923593716973,"score_spread":0.2398485527730355,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}