{"id":"W2952405725","doi":"10.48550/arxiv.1303.5294","title":"Variable Selection for Clustering and Classification","year":2013,"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":"University of Guelph","funders":"University of Guelph","keywords":"Cluster analysis; Computer science; Variable (mathematics); Feature selection; Data mining; Selection (genetic algorithm); Machine learning; Artificial intelligence; Clustering high-dimensional data; Subspace topology; Focus (optics); Pattern recognition (psychology); 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":[0.0002740347,0.0001626986,0.0001794091,0.000124802,0.000136346,0.0001615165,0.0004733241,0.0002381286,0.000006012739],"category_scores_gemma":[0.00001950502,0.0001849032,0.0000590344,0.0002089788,0.00002816688,0.0003442486,0.0005522299,0.0002230029,0.000006671862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008833612,"about_ca_system_score_gemma":0.00008094059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007311343,"about_ca_topic_score_gemma":0.00001162436,"domain_scores_codex":[0.9988367,0.00008284372,0.0001125242,0.0007376761,0.00003155605,0.0001986836],"domain_scores_gemma":[0.9991292,0.00007795663,0.0001395337,0.0004283658,0.0001356972,0.00008923642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007331008,0.00001734619,0.0001191442,0.00009400042,0.00002528409,9.494501e-7,0.00007322143,0.006355642,0.0004258534,0.9845545,0.0003181241,0.008008581],"study_design_scores_gemma":[0.0001309828,0.00001828099,0.0001850021,0.00002246991,0.00001970236,0.000002065793,0.000003296679,0.6507691,0.00004352638,0.3481036,0.0005667591,0.0001352166],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004597949,0.00002945771,0.9925959,0.00008540111,0.0003449022,0.0004063769,0.000003486281,0.0001358238,0.001800774],"genre_scores_gemma":[0.4019362,0.00003832349,0.5961943,0.00005648117,0.00006256921,0.000004471222,0.000004889418,0.000009681795,0.001693067],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6444135,"threshold_uncertainty_score":0.7540135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09676217619901079,"score_gpt":0.2097659010899836,"score_spread":0.1130037248909728,"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."}}