{"id":"W4389641434","doi":"10.1017/eds.2023.40","title":"A novel heuristic method for detecting overfit in unsupervised classification of climate model data","year":2023,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Climate variability and models","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Environment Research Council; Sight Research UK; UK Research and Innovation; National Science Foundation","keywords":"Overfitting; Computer science; Cluster analysis; Robustness (evolution); Heuristic; Machine learning; Artificial intelligence; Mixture model; Data mining; Class (philosophy); Gaussian; Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004314637,0.0001486236,0.0001850656,0.0001053824,0.000240118,0.00003817548,0.002632226,0.00005368475,0.0001133684],"category_scores_gemma":[0.0004400075,0.0001501417,0.00002283605,0.0007386414,0.0006108572,0.001852424,0.004821476,0.0001098116,0.00008627174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000221538,"about_ca_system_score_gemma":0.00003064906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002436222,"about_ca_topic_score_gemma":0.0001652684,"domain_scores_codex":[0.9971969,0.00003727605,0.0004291749,0.001250128,0.0005662324,0.0005203481],"domain_scores_gemma":[0.9971322,0.0002897106,0.0001381248,0.002336268,0.000002107497,0.0001015428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003081933,0.0002052396,0.01084768,0.00003192442,0.000002264286,6.051226e-7,0.0002938042,0.06222778,0.9159171,0.0001828594,0.00006928932,0.01019064],"study_design_scores_gemma":[0.0003737341,0.00002421489,0.06059742,0.00001400472,0.00001239612,0.000002405714,0.0002447841,0.9367129,0.001275631,0.0003808926,0.0002059599,0.0001556169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8231576,0.000008508883,0.1669672,0.0001636149,0.00009634873,0.0007270146,0.008278099,0.00005196374,0.000549592],"genre_scores_gemma":[0.8960974,0.0001082501,0.1024382,0.00005388105,0.000009708505,0.00002930588,0.001226635,0.00001599772,0.00002056969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9146414,"threshold_uncertainty_score":0.6122599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1606655707973861,"score_gpt":0.3548466895345715,"score_spread":0.1941811187371854,"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."}}