{"id":"W2603718738","doi":"10.1080/08839514.2017.1279046","title":"Performance Comparison of Recent Imputation Methods for Classification Tasks over Binary Data","year":2017,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Computer science; Naive Bayes classifier; Missing data; Support vector machine; Logistic regression; Artificial intelligence; Binary classification; Pattern recognition (psychology); Regression; Machine learning; Data mining; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.001165111,0.0001546031,0.0002499103,0.00007443407,0.0004897618,0.0002553628,0.002660143,0.0001031615,0.00001424715],"category_scores_gemma":[0.0001902277,0.0001521246,0.00003581086,0.0001520335,0.0001660477,0.0006107407,0.0005071575,0.0001505031,0.00002710052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002908393,"about_ca_system_score_gemma":0.0001022772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002591441,"about_ca_topic_score_gemma":0.000008186142,"domain_scores_codex":[0.9982855,0.00004558089,0.000603046,0.0006077221,0.0002023123,0.0002558799],"domain_scores_gemma":[0.9969271,0.0002182028,0.0005549884,0.002023339,0.000205576,0.00007074923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003202979,0.00008225203,0.00007086988,0.00002169572,0.000007907011,6.147464e-8,0.0003114902,0.0008481822,0.02912074,0.1625628,0.00008323068,0.8068587],"study_design_scores_gemma":[0.00002653926,0.00007460957,0.0006602263,0.00001551937,0.00001134016,3.639987e-7,0.00007290386,0.849851,0.1083181,0.04010134,0.0007146882,0.0001534078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01143751,0.00004284774,0.9859081,0.0004628284,0.0004484917,0.0003458241,0.00001074692,0.00006914097,0.001274544],"genre_scores_gemma":[0.6990217,0.00005915561,0.3007422,0.00003572343,0.00005881125,0.00003578644,0.00003206918,0.000007735958,0.000006884125],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8490028,"threshold_uncertainty_score":0.6203463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3734340380579709,"score_gpt":0.482600230886966,"score_spread":0.1091661928289951,"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."}}