{"id":"W4416011069","doi":"10.1287/mnsc.2023.03523","title":"Model Aggregation for Risk Evaluation and Robust Optimization","year":2025,"lang":"en","type":"article","venue":"Management Science","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Expected shortfall; Axiom; Equivalence (formal languages); Axiomatic system; Robust optimization; Value at risk; Risk management; Portfolio; Risk measure","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008335336,0.00008660083,0.00009798349,0.000765705,0.0006640925,0.0005519187,0.0004331483,0.0000299846,0.00002072647],"category_scores_gemma":[0.001465278,0.00007173425,0.00002876588,0.002091461,0.0001735352,0.0009384048,0.0001463138,0.00003282873,0.000006179865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007327785,"about_ca_system_score_gemma":0.00007427196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006540464,"about_ca_topic_score_gemma":0.000007487047,"domain_scores_codex":[0.9976429,0.00006193844,0.000343673,0.0005761018,0.001192803,0.000182617],"domain_scores_gemma":[0.9986182,0.0001380064,0.0002123121,0.000389249,0.0005962158,0.0000460077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008055028,0.000009659876,0.001676207,0.00000202157,0.000002509544,3.623648e-8,0.00005889054,0.7665882,0.000004582853,0.01347595,0.001061419,0.2171125],"study_design_scores_gemma":[0.0003572867,0.00001210308,0.003881053,0.000009577328,0.00004296591,1.116625e-7,0.0001570974,0.9259562,0.00005483065,0.06880048,0.0006567895,0.00007148767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009750593,0.00006764274,0.96484,0.0005673061,0.0002722667,0.0009067129,0.000004375337,0.00003022158,0.02356088],"genre_scores_gemma":[0.6666093,0.0007952015,0.3269757,0.0002489318,0.00001982686,0.0001490097,0.00001245672,0.000005578243,0.005183961],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6568587,"threshold_uncertainty_score":0.5322165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09926344080492287,"score_gpt":0.3983580275553127,"score_spread":0.2990945867503899,"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."}}