{"id":"W4322212746","doi":"10.5194/egusphere-egu23-16163","title":"A comparison of methods for determining the number of classes in unsupervised classification of climate models","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Climate variability and models","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Silhouette; Cluster analysis; Computer science; Robustness (evolution); Bayesian probability; Bayesian information criterion; Class (philosophy); Data mining; Artificial intelligence; Machine learning; Heuristic","routes":{"ca_aff":true,"ca_fund":false,"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":[0.02518645,0.001450447,0.001368517,0.005364433,0.001398216,0.002630552,0.00209536,0.002258885,0.001345099],"category_scores_gemma":[0.06702188,0.0006666384,0.00162516,0.002189466,0.001413302,0.003430843,0.002779884,0.002085844,0.0004754082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002476295,"about_ca_system_score_gemma":0.002430102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008363178,"about_ca_topic_score_gemma":0.01300939,"domain_scores_codex":[0.9855739,0.008141824,0.0009193188,0.001360806,0.003534661,0.0004694557],"domain_scores_gemma":[0.9355406,0.04516464,0.002273686,0.007882377,0.008065705,0.001072972],"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":[0.003024405,0.0005280302,0.03313539,0.001060509,0.001846287,0.00008354802,0.001583516,0.2878809,0.004963094,0.04046537,0.01040699,0.615022],"study_design_scores_gemma":[0.0001840789,0.0003527521,0.02459196,0.0002383221,0.0001677742,0.0001332141,0.0005150447,0.9301324,0.005099556,0.03416212,0.004223106,0.0001996352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2209444,0.005434582,0.7613965,0.001025958,0.0003664509,0.0004583145,0.001119058,0.002047098,0.007207783],"genre_scores_gemma":[0.499535,0.002019873,0.4903387,0.0002157626,0.0001956936,0.0006214794,0.0036675,0.001519475,0.001886528],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02518645,"threshold_uncertainty_score":0.1332003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2847627330567447,"score_gpt":0.4704680535724227,"score_spread":0.185705320515678,"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."}}