{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002595739,0.00009575886,0.0001164565,0.0001328185,0.0001405019,0.0001682943,0.0003719705,0.0001333274,0.000005656114],"category_scores_gemma":[0.001121881,0.0000830646,0.00003174833,0.0004176126,0.00006542305,0.0003486715,0.0001406442,0.0007648551,0.000005221963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002406014,"about_ca_system_score_gemma":0.0001496646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000104089,"about_ca_topic_score_gemma":0.000001803372,"domain_scores_codex":[0.9986503,0.0001299294,0.0002226595,0.0003525676,0.0005056791,0.0001389354],"domain_scores_gemma":[0.9979699,0.001421483,0.00006892784,0.0003598453,0.0001435954,0.00003625996],"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":[0.000005208812,0.00001268378,0.0001713382,0.0001145077,0.000003302384,0.000006392847,0.001003635,0.001333848,0.002141073,0.03174688,0.00008075018,0.9633804],"study_design_scores_gemma":[0.00008327306,0.0001324671,0.0008055404,0.0006017534,0.000004711936,0.000003719996,0.00001622683,0.9820402,0.007334488,0.008116451,0.0007635176,0.00009768409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003361184,0.0001978348,0.9932258,0.002200137,0.0002008526,0.00007477262,0.000002184792,0.0002919372,0.0004452892],"genre_scores_gemma":[0.8130567,0.00009354475,0.1862435,0.0004994174,0.00002948646,0.000009418494,0.000005163576,0.000008742133,0.00005400795],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9807063,"threshold_uncertainty_score":0.3387276,"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."}}