{"id":"W4404740887","doi":"10.1007/s11749-024-00958-2","title":"Distribution-free tests for lossless feature selection in classification and regression","year":2024,"lang":"en","type":"article","venue":"Test","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feature selection; Feature (linguistics); Selection (genetic algorithm); Regression; Statistics; Pattern recognition (psychology); Mathematics; Computer science; Artificial intelligence; Distribution (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05742384,0.002117493,0.003935966,0.004182752,0.001732422,0.003027036,0.006958268,0.004784393,0.007076502],"category_scores_gemma":[0.2616872,0.001361314,0.002512445,0.002770057,0.007726433,0.009343921,0.00515114,0.008388073,0.001632354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001825587,"about_ca_system_score_gemma":0.003700892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009859825,"about_ca_topic_score_gemma":0.0008257047,"domain_scores_codex":[0.9540502,0.03169062,0.002031278,0.004306532,0.006892916,0.001028421],"domain_scores_gemma":[0.6296808,0.3382237,0.005785462,0.0189446,0.005621303,0.001744168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003513713,0.00077693,0.01869081,0.001247262,0.001890758,0.001408584,0.0004301289,0.1147302,0.003837253,0.4227884,0.01859943,0.4120866],"study_design_scores_gemma":[0.0005022002,0.0005568166,0.003659272,0.0001362558,0.0001579195,0.0005744136,0.00007773664,0.4694095,0.003306971,0.5189858,0.002565017,0.00006813551],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006804822,0.0003167326,0.9908549,0.0005303207,0.00009362007,0.00006748477,0.0002093275,0.0005943807,0.0005283991],"genre_scores_gemma":[0.5418714,0.000738919,0.4418403,0.001642041,0.001197005,0.00160838,0.002935245,0.001064848,0.007101863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05742384,"threshold_uncertainty_score":0.30369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1056891819183642,"score_gpt":0.417041700541995,"score_spread":0.3113525186236308,"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."}}