{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01029786,0.002107518,0.002756294,0.005535902,0.001876065,0.003003781,0.003038458,0.002446072,0.004795736],"category_scores_gemma":[0.02732057,0.0009944419,0.002198933,0.007699814,0.002274441,0.002201542,0.00308599,0.004189755,0.003044705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002047452,"about_ca_system_score_gemma":0.002782126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005113321,"about_ca_topic_score_gemma":0.004169832,"domain_scores_codex":[0.9889498,0.006861533,0.0003767314,0.00156017,0.001987029,0.0002646352],"domain_scores_gemma":[0.9912207,0.005959922,0.0005805792,0.0009748029,0.001099046,0.000165089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001399807,0.0001040164,0.002731586,0.0009595704,0.0007336623,0.0001446715,0.000468463,0.1574813,0.001900156,0.2439506,0.02292114,0.5684647],"study_design_scores_gemma":[0.00005044178,0.00005645135,0.001353515,0.0002268743,0.00007189935,0.0001446697,0.0001035395,0.5550947,0.001532302,0.4131765,0.0281146,0.00007448111],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001125003,0.002659962,0.9937567,0.0005115586,0.0001276353,0.0000888084,0.0001656094,0.0005201651,0.001044678],"genre_scores_gemma":[0.05568743,0.003813283,0.9349713,0.0003322207,0.0005824908,0.0008117869,0.001098204,0.0003345279,0.002368805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01029786,"threshold_uncertainty_score":0.05446094,"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."}}