{"id":"W2278599087","doi":"10.24148/wp2015-14","title":"Aggregation level in stress testing models","year":2015,"lang":"en","type":"article","venue":"Federal Reserve Bank of San Francisco, Working Paper Series","topic":"Credit Risk and Financial Regulations","field":"Economics, Econometrics and Finance","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Portfolio; Econometrics; Stress test; Stress testing (software); Computer science; Aggregate (composite); Sample (material); Loan; Portfolio optimization; Economics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005976704,0.0002099112,0.0005015307,0.0002722207,0.0001627619,0.0001247546,0.0002875998,0.0001601509,0.00004878433],"category_scores_gemma":[0.0007332632,0.0002448938,0.00008589299,0.0006691614,0.000111627,0.000993537,0.0001144832,0.0002249522,0.00002999931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001198154,"about_ca_system_score_gemma":0.00007809551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002282451,"about_ca_topic_score_gemma":0.006945271,"domain_scores_codex":[0.9981542,0.00002594393,0.0008901125,0.0004025406,0.0001323658,0.0003948827],"domain_scores_gemma":[0.9989002,0.0001052445,0.0004036728,0.0003616931,0.0001247013,0.0001044795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001492496,0.0001110715,0.8435113,0.00005906202,0.00002288968,0.00001107121,0.0022162,0.01935017,0.0000821628,0.1237371,0.0007924588,0.009957269],"study_design_scores_gemma":[0.001423683,0.0002124742,0.7601222,0.0005034238,0.000005467902,0.000005247507,0.0006142634,0.01035767,0.0003896792,0.2144183,0.0113565,0.000591103],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9363892,0.005583807,0.003699417,0.0004584813,0.0007350834,0.0003209707,0.0001657332,0.00006576224,0.05258151],"genre_scores_gemma":[0.9926046,0.00006988377,0.006037256,0.00002535866,0.0002433129,0.00003533469,0.00004207002,0.00003522199,0.0009070073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09068128,"threshold_uncertainty_score":0.998648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1642234754017599,"score_gpt":0.256501759407499,"score_spread":0.09227828400573909,"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."}}