{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002232626,0.0001100394,0.0003631227,0.00006062666,0.000168703,0.00005464591,0.0003620544,0.00004550069,0.00001314801],"category_scores_gemma":[0.02207563,0.0000670974,0.00006915527,0.0004752559,0.0001486116,0.00008886629,0.00006543544,0.0002982557,0.00000401456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001275554,"about_ca_system_score_gemma":0.0001308479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007218563,"about_ca_topic_score_gemma":0.000008476321,"domain_scores_codex":[0.9981394,0.0003773391,0.0003814654,0.0001680066,0.0007057192,0.0002280937],"domain_scores_gemma":[0.9873747,0.01030839,0.001394672,0.0002752557,0.0005630475,0.00008396435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0009225874,0.0002213675,0.04250619,0.0001125447,0.0005800296,0.000009592752,0.0001593822,0.00002124657,0.0005975679,0.2146483,0.4743011,0.2659201],"study_design_scores_gemma":[0.0006587173,0.0002567575,0.5855207,0.00005205963,0.0002475597,0.00001078425,0.0002414231,0.01851176,0.00003183154,0.3886354,0.005710291,0.0001226978],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009823595,0.000003893236,0.9797078,0.008093997,0.0002534637,0.00019451,0.00181215,0.00002353464,0.00008699831],"genre_scores_gemma":[0.411249,0.000009523772,0.587368,0.000301677,0.0006022063,0.00001242973,0.0001407042,0.00002301577,0.0002934612],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5430145,"threshold_uncertainty_score":0.9861618,"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."}}