{"id":"W1627302939","doi":"10.1093/oxfordhb/9780199857944.013.010","title":"Data-Driven Model Evaluation","year":2014,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Nonparametric statistics; Series (stratigraphy); Function (biology); Nested set model; Parametric statistics; Parametric model; Computer science; Sample (material); Algorithm; Mathematics; Statistics; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.01316263,0.00164289,0.001580316,0.001769467,0.0004806934,0.003078329,0.002274512,0.001983821,0.0117912],"category_scores_gemma":[0.04160319,0.0005153278,0.001480861,0.001198333,0.0005891055,0.002390894,0.002613873,0.002144345,0.002779942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001147936,"about_ca_system_score_gemma":0.001765287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002042491,"about_ca_topic_score_gemma":0.002619312,"domain_scores_codex":[0.995658,0.002374098,0.0002361662,0.0004218612,0.001156221,0.0001536461],"domain_scores_gemma":[0.9865239,0.00904009,0.000462844,0.001596129,0.002124136,0.0002528969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005287562,0.0002478966,0.00581653,0.0009817323,0.0004757494,0.0003594267,0.0001908442,0.6115136,0.00333618,0.07381006,0.02692811,0.2758111],"study_design_scores_gemma":[0.00003384732,0.000105666,0.0004815611,0.00008912846,0.00003474201,0.0001089223,0.00006791447,0.961168,0.002172145,0.02946319,0.00625008,0.00002488508],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02111497,0.001198831,0.9621828,0.0007141145,0.0001992138,0.0004122294,0.002427821,0.001902982,0.009847118],"genre_scores_gemma":[0.3285517,0.0009704399,0.6513003,0.0006112464,0.0001253034,0.001174431,0.008715289,0.001028981,0.007522332],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01316263,"threshold_uncertainty_score":0.06961149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.275953032011104,"score_gpt":0.3537974986639438,"score_spread":0.07784446665283984,"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."}}