{"id":"W4200534113","doi":"10.1002/eap.2524","title":"Automatic selection of the number of clusters using Bayesian clustering and sparsity‐inducing priors","year":2021,"lang":"en","type":"article","venue":"Ecological Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Biodiversity Monitoring Institute; University of Alberta","funders":"Fundação de Apoio ao Desenvolvimento do Ensino, Ciência e Tecnologia do Estado de Mato Grosso do Sul; National Science Foundation of Sri Lanka; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Cluster analysis; Prior probability; Computer science; Bayesian probability; Context (archaeology); Model selection; Mixture model; Data mining; Machine learning; Ecology; Artificial intelligence; Geography; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002215749,0.00006705732,0.0001490742,0.00002075802,0.0001462174,0.0000229233,0.0002376394,0.00006813196,0.00003017209],"category_scores_gemma":[0.00003687319,0.00004987358,0.00005067815,0.0004528733,0.00006211791,0.0000812837,0.0003038689,0.000096989,8.100976e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002900335,"about_ca_system_score_gemma":0.00005871139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009954928,"about_ca_topic_score_gemma":0.00001966863,"domain_scores_codex":[0.9992281,0.0001198425,0.0002197701,0.0002225955,0.00009391546,0.0001158131],"domain_scores_gemma":[0.9993888,0.0001159592,0.0001196205,0.0002685432,0.00006787067,0.00003921279],"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":[0.000006306987,0.0009633217,0.05237368,0.0005266629,0.0001486044,0.000004852116,0.002654711,0.00388518,0.1359168,0.3955492,0.00008742207,0.4078833],"study_design_scores_gemma":[0.0001697359,0.00001673181,0.07397173,0.00003920868,0.00003271717,0.0001006044,0.00003642307,0.8856265,0.01081092,0.02897082,0.00009453444,0.0001300884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2402676,0.00001200766,0.7588211,0.0002779385,0.00003126994,0.0001572108,7.709905e-7,0.00002166418,0.0004103958],"genre_scores_gemma":[0.5530913,0.000002491744,0.4468027,0.000060199,0.000009507142,0.00001184501,1.886484e-7,0.000001948321,0.00001983685],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8817413,"threshold_uncertainty_score":0.2033786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02234428768907278,"score_gpt":0.2865101636616942,"score_spread":0.2641658759726215,"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."}}