{"id":"W6913191396","doi":"10.5683/sp3/iamlij","title":"A bootstrapping method corrected for a substantial proportion of overestimation of test accuracy estimates when optimal cutoffs and accuracy were estimated simultaneously","year":2025,"lang":"en","type":"dataset","venue":"Borealis","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Bootstrapping (finance); Cutoff; Accuracy and precision; Observational error; Sampling (signal processing); Sample size determination","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02418167,0.002749959,0.002291627,0.004200494,0.001451243,0.002760402,0.003696009,0.001975632,0.00538715],"category_scores_gemma":[0.074404,0.0008137112,0.001653172,0.004779265,0.001238153,0.001596534,0.001929923,0.002321033,0.007743474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001612009,"about_ca_system_score_gemma":0.001953088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01430427,"about_ca_topic_score_gemma":0.04234457,"domain_scores_codex":[0.9877234,0.004707477,0.001601118,0.003221901,0.002207948,0.0005382507],"domain_scores_gemma":[0.9609503,0.02043051,0.001681209,0.00992216,0.006569962,0.0004459165],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002546339,0.00053876,0.1005418,0.003201396,0.002298535,0.0003697723,0.000631813,0.02134109,0.0105327,0.004874433,0.66271,0.1904133],"study_design_scores_gemma":[0.001599282,0.0006504215,0.157664,0.000787761,0.001735391,0.001257065,0.0005293172,0.08885178,0.02845019,0.02885425,0.6890842,0.0005363355],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1157222,0.003829801,0.1250646,0.001109719,0.001288848,0.001172423,0.7099009,0.02339075,0.01852087],"genre_scores_gemma":[0.1240106,0.0003257038,0.1058354,0.0007215615,0.0001135708,0.001803088,0.7593868,0.002953121,0.004850131],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9758183,"threshold_uncertainty_score":0.1278865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03332450544884148,"score_gpt":0.3531704416309692,"score_spread":0.3198459361821277,"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."}}