{"id":"W4361205542","doi":"10.1080/01621459.2023.2195976","title":"Feature Screening with Conditional Rank Utility for Big-Data Classification","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Categorical variable; Cru; Estimator; Feature (linguistics); Computer science; Outlier; Rank (graph theory); Data mining; Constructive; Artificial intelligence; Statistics; Mathematics; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0179844,0.001833758,0.002366393,0.003111917,0.001039187,0.001905463,0.002804197,0.001857558,0.002331735],"category_scores_gemma":[0.07181957,0.0005866541,0.0015871,0.003713198,0.003129184,0.003609156,0.003500084,0.003297992,0.0008264092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001333371,"about_ca_system_score_gemma":0.003164349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002057207,"about_ca_topic_score_gemma":0.001964742,"domain_scores_codex":[0.9891726,0.007075013,0.0003896205,0.001019677,0.001968352,0.0003747994],"domain_scores_gemma":[0.954641,0.03327482,0.002599321,0.005259551,0.003468749,0.0007564159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005951985,0.0003591468,0.01204921,0.0006889066,0.0003227544,0.0005578924,0.0003508441,0.3415073,0.004603074,0.3095744,0.009432741,0.3199585],"study_design_scores_gemma":[0.00003189766,0.0001017332,0.0008887022,0.00002659726,0.00002491892,0.00007454827,0.00002766951,0.8794814,0.001449541,0.1168011,0.001056167,0.00003577663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004152792,0.0002247738,0.9946202,0.0001834813,0.00002098835,0.00008194428,0.00008085162,0.000340387,0.0002945267],"genre_scores_gemma":[0.4235993,0.0006407819,0.5703853,0.0006110572,0.0002780595,0.0009879642,0.001033972,0.0002983129,0.002165287],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0179844,"threshold_uncertainty_score":0.09511179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2304884306171918,"score_gpt":0.4237758304602459,"score_spread":0.1932873998430541,"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."}}