{"id":"W4386035726","doi":"10.1214/23-aos2289","title":"Optimal discriminant analysis in high-dimensional latent factor models","year":2023,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Minimax; Mathematics; Linear discriminant analysis; Discriminant; Classifier (UML); Pattern recognition (psychology); Principal component analysis; Latent variable; Artificial intelligence; Dimension (graph theory); Sample size determination; Dimensionality reduction; Logarithm; Latent variable model; Statistics; Mathematical optimization; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.000140104,0.00007251179,0.0001176104,0.00009313275,0.00003260965,0.000007074333,0.0001323089,0.00004188338,0.00002344729],"category_scores_gemma":[0.00003460547,0.00005023244,0.00005135321,0.0003052312,0.00005037562,0.00000223852,0.00007242132,0.00004183427,0.000006191095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000308669,"about_ca_system_score_gemma":0.00003575817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000541899,"about_ca_topic_score_gemma":0.00003337035,"domain_scores_codex":[0.9993222,0.00004553278,0.0001871683,0.0001532937,0.000152451,0.0001393503],"domain_scores_gemma":[0.9995276,0.00002179694,0.00008159612,0.0002436577,0.00009122818,0.00003417072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0003514471,0.000183551,0.003202257,0.00004034367,0.0004645905,0.000008618207,0.0006101843,0.5347303,0.3915132,0.009645108,0.05058184,0.008668616],"study_design_scores_gemma":[0.0007723875,0.000338871,0.5555357,0.00003277239,0.0001999611,0.000001459785,0.0003612956,0.212358,0.2194605,0.008536263,0.001973405,0.0004293512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9708564,0.0001212384,0.02766926,0.0006991985,0.00005549474,0.00007330039,0.000479396,0.00000563554,0.00004012284],"genre_scores_gemma":[0.9975156,0.0004286315,0.001050734,0.0001120286,0.00002379531,0.00001030962,0.0003764699,0.00000739401,0.0004750484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5523334,"threshold_uncertainty_score":0.204842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0983438622062266,"score_gpt":0.3423473871007673,"score_spread":0.2440035248945407,"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."}}