{"id":"W4414434407","doi":"10.1287/mnsc.2023.01659","title":"E-backtesting","year":2025,"lang":"en","type":"article","venue":"Management Science","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Risk measure; Measure (data warehouse); Basel II; Risk management; Expected shortfall; Identification (biology); Basel III; Market risk; Financial market","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01560463,0.001977836,0.002572139,0.003535529,0.001148621,0.002223771,0.002657062,0.00215483,0.01252619],"category_scores_gemma":[0.09794011,0.0006233794,0.002166843,0.002022175,0.002442384,0.003998878,0.003218382,0.002650075,0.002889765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009455155,"about_ca_system_score_gemma":0.001414078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001055882,"about_ca_topic_score_gemma":0.0009282031,"domain_scores_codex":[0.98647,0.007464627,0.0008475601,0.002276306,0.002360024,0.0005814907],"domain_scores_gemma":[0.9125297,0.06684804,0.003345264,0.010725,0.005782529,0.0007695449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001484237,0.0006797633,0.02245113,0.0007622404,0.0005654121,0.0009251625,0.0007725165,0.2068528,0.00744609,0.1198054,0.01387029,0.6243851],"study_design_scores_gemma":[0.0001857444,0.0007618461,0.004068821,0.000173955,0.0001267048,0.0005987879,0.000233181,0.8298785,0.0182297,0.1369315,0.008666888,0.0001443142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02980757,0.00029216,0.9637338,0.0002110203,0.0001704083,0.0003169374,0.0004231876,0.001947951,0.00309695],"genre_scores_gemma":[0.542855,0.0002796832,0.4460956,0.0006275271,0.0001993302,0.001297469,0.002433096,0.001080319,0.005132058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01560463,"threshold_uncertainty_score":0.08252615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06099032342716247,"score_gpt":0.4177832286398843,"score_spread":0.3567929052127218,"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."}}