{"id":"W3121915488","doi":"10.1002/wilm.10565","title":"Stress-Testing With Parametric Models and Fully Flexible Probabilities","year":2017,"lang":"en","type":"article","venue":"Wilmott","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Université Laval","keywords":"Stress testing (software); Parametric statistics; Computer science; Stress (linguistics); Econometrics; Mathematics; Statistics; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002665768,0.0001162294,0.0002012194,0.00003787031,0.0002673302,0.0001975,0.0001682893,0.00004320317,0.0000260723],"category_scores_gemma":[0.004571144,0.00008250239,0.00001359163,0.00006443876,0.0002187458,0.000168681,0.00008602404,0.0001073224,0.000003418529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001100318,"about_ca_system_score_gemma":0.00003667325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008934216,"about_ca_topic_score_gemma":0.00001031189,"domain_scores_codex":[0.9992341,0.00003749671,0.0001524128,0.0002089658,0.0001598975,0.0002071409],"domain_scores_gemma":[0.9980193,0.001224637,0.0001260097,0.0004430308,0.0001074414,0.00007956634],"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":[0.00002632531,0.00007404009,0.02002648,0.0003507437,0.000021982,0.00001074984,0.0002846116,0.00004152131,0.00002771169,0.9093719,0.0001431749,0.0696208],"study_design_scores_gemma":[0.0002367668,0.0001763063,0.01124769,0.0001648319,0.00002454836,0.00001031281,0.0000899919,0.01707441,0.0002188638,0.9705796,0.00003120226,0.0001454428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.662351,0.00009768981,0.2835138,0.0001944426,0.00006297744,0.0003505266,0.0000405315,0.0001289916,0.05326015],"genre_scores_gemma":[0.5272793,0.000003881083,0.4723755,0.00001176022,0.00002504603,0.00001381064,2.423404e-7,0.00001003904,0.0002804835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1888617,"threshold_uncertainty_score":0.5472416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2576569299586397,"score_gpt":0.3851261096572892,"score_spread":0.1274691796986495,"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."}}