{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006291397,0.00006405756,0.0001234416,0.00005173766,0.00007720165,0.0001814196,0.0001526841,0.00002378749,0.00001518128],"category_scores_gemma":[0.02007325,0.00003578133,0.00001832605,0.0001080439,0.0001411639,0.0004566365,0.00003892389,0.0002197538,0.000004233809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001174943,"about_ca_system_score_gemma":0.00004941935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004313637,"about_ca_topic_score_gemma":0.000002488589,"domain_scores_codex":[0.9981579,0.001166383,0.0002777286,0.0001355516,0.0001919265,0.00007048499],"domain_scores_gemma":[0.9689729,0.03053599,0.000144009,0.00016801,0.0001125291,0.00006656285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006104739,0.0000367222,0.00007169215,0.00005261361,0.00001864801,0.000004742089,0.0008123173,0.00004238947,0.0001710311,0.9438689,0.0004074292,0.05390306],"study_design_scores_gemma":[0.0002568909,0.0006170366,0.03080955,0.0001248907,0.00006321282,0.0002151737,0.0003979178,0.02674156,0.00006682637,0.9329739,0.007656793,0.00007630088],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02734028,0.0002884906,0.9563127,0.0144712,0.0001001428,0.000111033,0.00001336036,0.00001197333,0.001350814],"genre_scores_gemma":[0.9727797,0.00004409232,0.02694858,0.0001515483,0.00002639253,0.000003538068,8.742669e-7,0.000002979228,0.0000422873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9454394,"threshold_uncertainty_score":0.9881811,"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."}}