{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004422264,0.0001670475,0.0001917388,0.0001903887,0.0001694134,0.0001442436,0.0005029006,0.000240797,0.000002368111],"category_scores_gemma":[0.00002839435,0.0001992063,0.00006884137,0.0004104908,0.00002746993,0.0002612691,0.0007002846,0.0002377796,0.000009089185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001007709,"about_ca_system_score_gemma":0.000109066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006530112,"about_ca_topic_score_gemma":0.00002311659,"domain_scores_codex":[0.9986846,0.00008045032,0.0001239517,0.0008442466,0.00003911198,0.0002275959],"domain_scores_gemma":[0.9991207,0.00009214528,0.0001332904,0.0004558575,0.0001125008,0.00008547844],"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":[0.00001432536,0.00001963028,0.0001728174,0.0001678612,0.00004078499,0.000003229932,0.00009351772,0.03424954,0.0004032901,0.958697,0.0006470553,0.005490991],"study_design_scores_gemma":[0.0001461175,0.00002102623,0.0002982086,0.00003404883,0.00002372566,0.000001716118,0.000005314454,0.6696231,0.0000744088,0.3291164,0.0005087361,0.0001471761],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001235816,0.00001977276,0.996227,0.0001348803,0.0005471669,0.0003494694,0.000007474688,0.0003925918,0.001085828],"genre_scores_gemma":[0.3312437,0.00008294783,0.6590719,0.00007156184,0.0001174656,0.000006861575,0.00001165559,0.00002533064,0.009368517],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6353735,"threshold_uncertainty_score":0.8123397,"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."}}