{"id":"W4391540853","doi":"10.1007/s43681-023-00415-0","title":"Evaluating trustworthiness of decision tree learning algorithms based on equivalence checking","year":2024,"lang":"en","type":"article","venue":"AI and Ethics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"New York Institute of Technology; Bishop's University; Université du Québec à Montréal; Université de Sherbrooke; Université du Québec en Outaouais","funders":"","keywords":"Decision tree; Trustworthiness; Equivalence (formal languages); Computer science; ID3 algorithm; Decision tree learning; Algorithm; Incremental decision tree; Theoretical computer science; Machine learning; Artificial intelligence; Mathematics; Discrete mathematics; Computer security","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":[0.1036138,0.0009856983,0.002038918,0.005026523,0.001721206,0.005457778,0.002777877,0.003531997,0.002123029],"category_scores_gemma":[0.4698097,0.0006515094,0.001744498,0.002595953,0.004562177,0.008685424,0.004243969,0.003789893,0.000384323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003157494,"about_ca_system_score_gemma":0.004319231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002247024,"about_ca_topic_score_gemma":0.001373652,"domain_scores_codex":[0.8902609,0.06024617,0.00805992,0.006972449,0.03237018,0.002090325],"domain_scores_gemma":[0.2930003,0.6270036,0.02360621,0.02925072,0.02423803,0.002901121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008361983,0.001287113,0.2056898,0.001293504,0.002331246,0.0005878345,0.002251789,0.3279338,0.005070455,0.1284728,0.004957137,0.3117625],"study_design_scores_gemma":[0.0002256429,0.0005781496,0.008177699,0.0001906635,0.0002157828,0.0002341183,0.0002966338,0.8792854,0.003930954,0.1058185,0.001000523,0.00004586711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4944302,0.001853388,0.4930687,0.002715708,0.0003369775,0.000456147,0.0004198071,0.0005837119,0.006135366],"genre_scores_gemma":[0.9583394,0.000166212,0.04041981,0.0001425267,0.0001203999,0.00009506755,0.0003765702,0.00006059961,0.0002794822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1036138,"threshold_uncertainty_score":0.5479689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1207564725191268,"score_gpt":0.430731319847737,"score_spread":0.3099748473286102,"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."}}