{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002323069,0.00006752162,0.00008984059,0.00002878138,0.00004357304,0.0000495682,0.00004793184,0.00007325125,0.00001387855],"category_scores_gemma":[0.005122421,0.00005063786,0.00001368426,0.0001668399,0.000027727,0.00004622235,0.00001707976,0.0001107659,0.000003478561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004498781,"about_ca_system_score_gemma":0.00002199995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005317806,"about_ca_topic_score_gemma":0.00002502453,"domain_scores_codex":[0.9995415,0.00002357941,0.0001085582,0.000160001,0.00006747673,0.00009884159],"domain_scores_gemma":[0.9974284,0.002386627,0.00002445027,0.00008680355,0.00004469949,0.00002903429],"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":[0.00001537508,0.00008781807,0.007886031,0.0004979876,0.000004841736,0.000002727949,0.0001115872,1.582427e-7,0.006259917,0.8642446,0.04397131,0.0769176],"study_design_scores_gemma":[0.0002304712,0.00009474753,0.130521,0.0004108982,0.00002053049,0.00001023036,0.00003186242,0.02801602,0.0008004392,0.8363367,0.003414443,0.0001126104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1691001,0.0007516341,0.8205101,0.005374268,0.0003460551,0.0009632789,0.000847968,0.0003749504,0.001731679],"genre_scores_gemma":[0.8607093,0.00002554862,0.1384402,0.00001930887,0.0001093014,0.00007987893,0.00004154288,0.00001421225,0.0005607278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6916092,"threshold_uncertainty_score":0.6132387,"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."}}