{"id":"W4404070406","doi":"10.1186/s41512-024-00179-z","title":"The relative data hungriness of unpenalized and penalized logistic regression and ensemble-based machine learning methods: the case of calibration","year":2024,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Sunnybrook Hospital; University of Toronto; Vector Institute; Sunnybrook Health Science Centre","funders":"","keywords":"Calibration; Logistic regression; Ensemble learning; Artificial intelligence; Computer science; Machine learning; Regression; Statistics; Pattern recognition (psychology); Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008318507,0.0001748146,0.0003713783,0.0001014935,0.0005058996,0.0001290824,0.0002125745,0.00008589667,0.00001437425],"category_scores_gemma":[0.116194,0.00008648924,0.00002794113,0.0003444967,0.001170442,0.0001518134,0.0004569687,0.0005893557,3.332091e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001096604,"about_ca_system_score_gemma":0.0001132056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002466294,"about_ca_topic_score_gemma":0.00005414904,"domain_scores_codex":[0.9952449,0.003175554,0.0005033804,0.0004472255,0.0003358494,0.0002931507],"domain_scores_gemma":[0.7953557,0.2038414,0.0001170345,0.0003778788,0.0002145029,0.00009340535],"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":[0.0003849059,0.0000829327,0.0009690537,0.002017217,0.0001364976,0.0004978736,0.001225076,0.0000303686,0.0005797398,0.7499175,0.0002148409,0.243944],"study_design_scores_gemma":[0.0005902813,0.0002902942,0.0002174233,0.0009774286,0.0002083798,0.0001670844,0.0004839211,0.3689601,0.0005215493,0.6269324,0.0005300629,0.0001210858],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0255511,0.01799535,0.9540021,0.001036381,0.00005649695,0.001082469,0.0001220443,0.00002606905,0.0001280126],"genre_scores_gemma":[0.7997692,0.002521607,0.1973825,0.000009291917,0.00003077947,0.00009563758,0.00003348565,0.0000307089,0.0001267709],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7742181,"threshold_uncertainty_score":0.8912506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4383443273239946,"score_gpt":0.5765325733102753,"score_spread":0.1381882459862807,"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."}}