{"id":"W4394993814","doi":"10.1007/s42519-024-00376-5","title":"On the Capability of Classification Trees and Random Forests to Estimate Probabilities","year":2024,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Practice","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Random forest; Statistics; Artificial intelligence","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":[0.04731533,0.001846782,0.001985468,0.004622363,0.00180549,0.002893214,0.002434881,0.003244326,0.001532054],"category_scores_gemma":[0.2604274,0.001094699,0.001567091,0.00308703,0.004422958,0.007553969,0.002893099,0.003753867,0.0007134798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00140486,"about_ca_system_score_gemma":0.00210215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0112382,"about_ca_topic_score_gemma":0.005152344,"domain_scores_codex":[0.9747502,0.01715703,0.001059906,0.002137737,0.004181383,0.0007136673],"domain_scores_gemma":[0.6940989,0.281028,0.006800154,0.008162634,0.009118485,0.0007919018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000419869,0.00009994032,0.01121109,0.0003445427,0.0002429867,0.0001556052,0.0004621872,0.7874118,0.001072688,0.08086768,0.002609591,0.115102],"study_design_scores_gemma":[0.00003702269,0.000109434,0.001531055,0.0001853687,0.0000407749,0.0001466189,0.00006511692,0.9137995,0.0008902359,0.08190019,0.001241589,0.00005312661],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04632418,0.004265164,0.943455,0.001304551,0.0001418755,0.0001013056,0.0002300762,0.0005168077,0.00366096],"genre_scores_gemma":[0.5775469,0.0038,0.4146605,0.0009699708,0.0005628857,0.0003511107,0.0006794979,0.0003326634,0.001096502],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04731533,"threshold_uncertainty_score":0.2502304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0296397589164158,"score_gpt":0.3635069484470442,"score_spread":0.3338671895306284,"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."}}