{"id":"W4406271657","doi":"10.48550/arxiv.2501.04903","title":"Analyzing decision tree bias towards the minority class","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Decision tree; Computer science; Psychology; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03344369,0.0006252561,0.001087567,0.001721276,0.00116355,0.002073848,0.001410487,0.001521312,0.001975238],"category_scores_gemma":[0.1704779,0.0002774958,0.0007453699,0.001422079,0.002186041,0.002842195,0.00197423,0.002817525,0.0005517185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001170805,"about_ca_system_score_gemma":0.001010152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001673469,"about_ca_topic_score_gemma":0.001536754,"domain_scores_codex":[0.989759,0.006237695,0.0003627739,0.00128949,0.001862856,0.0004882936],"domain_scores_gemma":[0.7697755,0.1946133,0.01071911,0.01406893,0.009362186,0.001461035],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002922519,0.0003962393,0.2953578,0.0007175877,0.0009427022,0.0006751995,0.002733803,0.2729416,0.00587055,0.165774,0.0144,0.2372678],"study_design_scores_gemma":[0.0001253301,0.0002226428,0.02760342,0.0003328092,0.0002096224,0.0004687124,0.0005545091,0.7392737,0.006510175,0.218985,0.005658024,0.00005613513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5680134,0.00251593,0.4200053,0.002434956,0.0002854941,0.0001452542,0.0005669593,0.0003520592,0.005680699],"genre_scores_gemma":[0.967073,0.0003037212,0.03043201,0.000490131,0.000209469,0.00008578893,0.0005784586,0.0001007845,0.0007266873],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03344369,"threshold_uncertainty_score":0.1768693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1373005555953687,"score_gpt":0.2346794760199175,"score_spread":0.09737892042454885,"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."}}