{"id":"W4378713334","doi":"10.48550/arxiv.2305.16464","title":"Flexible Variable Selection for Clustering and Classification","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Killam Trusts; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Cluster analysis; Variable (mathematics); Skewness; Selection (genetic algorithm); Feature selection; Computer science; Mixture model; Cluster (spacecraft); Data mining; Gaussian; Transformation (genetics); Artificial intelligence; Pattern recognition (psychology); Machine learning; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01509655,0.002225262,0.002891979,0.005636027,0.00224239,0.00359707,0.003643954,0.002155541,0.006080051],"category_scores_gemma":[0.04159439,0.0009527558,0.002974883,0.007844711,0.002423159,0.00260052,0.004178294,0.004508205,0.003607111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001913931,"about_ca_system_score_gemma":0.002907903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003990816,"about_ca_topic_score_gemma":0.003337051,"domain_scores_codex":[0.9836819,0.01074916,0.0005380293,0.002513794,0.002071033,0.0004461754],"domain_scores_gemma":[0.9847838,0.01014554,0.0009077067,0.002066188,0.001763782,0.0003329866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002560579,0.0001388427,0.004125,0.0006669664,0.0007474757,0.0001880374,0.0005129644,0.2010408,0.002594664,0.1667924,0.02207757,0.6008592],"study_design_scores_gemma":[0.00006654258,0.00006749771,0.00139451,0.0001632212,0.00007315371,0.0001247821,0.0001031027,0.7014117,0.0018711,0.2754638,0.01919446,0.00006610715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001431927,0.0006450447,0.9959347,0.0002688951,0.00007294367,0.00008399464,0.0001577527,0.0008305837,0.0005740937],"genre_scores_gemma":[0.07179982,0.0008872058,0.9219167,0.0003211119,0.0002715681,0.0008153385,0.001495004,0.0006726248,0.001820587],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01509655,"threshold_uncertainty_score":0.07983911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1737566016930563,"score_gpt":0.2371674064934387,"score_spread":0.06341080480038241,"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."}}