{"id":"W4405765420","doi":"10.48550/arxiv.2412.16209","title":"Challenges in the calibration of tree-based models for imbalanced classification","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperparameter; Tree (set theory); Machine learning; Artificial intelligence; Statistics; Econometrics; Random forest; Computer science; Mathematics; Psychology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06169298,0.001141258,0.002293076,0.00193472,0.001439124,0.005078598,0.004665431,0.003487152,0.001823733],"category_scores_gemma":[0.2571467,0.001643217,0.00153209,0.002285021,0.004439112,0.007007959,0.003977907,0.009170295,0.001132675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003544642,"about_ca_system_score_gemma":0.002691815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004924921,"about_ca_topic_score_gemma":0.003226828,"domain_scores_codex":[0.9706948,0.02109301,0.001174188,0.003005295,0.003447993,0.0005847085],"domain_scores_gemma":[0.862736,0.1125239,0.00620074,0.01098364,0.006841681,0.0007140902],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001727978,0.0001018645,0.01012266,0.0005005778,0.000317487,0.0002341074,0.001092985,0.5905873,0.0007553393,0.2816152,0.008146008,0.1063537],"study_design_scores_gemma":[0.00002901662,0.00003246708,0.001182659,0.0002345818,0.00002285251,0.0001427596,0.0001513991,0.5149422,0.0006287684,0.4779143,0.00466979,0.00004908422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0158191,0.001757961,0.9712312,0.006852823,0.0002527173,0.0001388639,0.0003361402,0.0005707338,0.003040486],"genre_scores_gemma":[0.6192422,0.003054657,0.3675385,0.004246236,0.0009099778,0.001046629,0.001042261,0.0006766106,0.002242928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.938307,"threshold_uncertainty_score":0.3262675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2207264365983063,"score_gpt":0.2518108476678467,"score_spread":0.03108441106954041,"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."}}