{"id":"W2286080795","doi":"10.2139/ssrn.2247023","title":"Moving the Goalposts: Subjective Performance Benchmarks and the Aumann-Serrano Measure of Riskiness","year":2013,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Measure (data warehouse); Econometrics; Economics; Statistics; Computer science; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003655819,0.0001449151,0.0003248392,0.00008650628,0.0004791056,0.00008532876,0.0003563769,0.00007957371,0.00005700687],"category_scores_gemma":[0.00021173,0.00009197552,0.0001263932,0.0001918807,0.0001931159,0.0003900323,0.00005813728,0.001297593,0.00001740494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002182461,"about_ca_system_score_gemma":0.0002186613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001694365,"about_ca_topic_score_gemma":0.0005200125,"domain_scores_codex":[0.9982073,0.00005528641,0.0005473848,0.0001967383,0.00007482073,0.0009184236],"domain_scores_gemma":[0.9990498,0.0001230349,0.0004359669,0.00023308,0.0001237722,0.00003437294],"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":[0.0002130925,0.00004982134,0.1461035,0.00002647277,0.0002193866,2.111195e-7,0.003473734,0.0004490969,0.00002506517,0.8116024,0.00006653855,0.03777071],"study_design_scores_gemma":[0.001849065,0.0001815082,0.1696448,0.00004795955,0.00002840685,0.00007005848,0.002519756,0.04998423,0.00003784375,0.7748331,0.0005485491,0.0002546766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9700455,0.01964287,0.005020754,0.001079302,0.0001678236,0.0002753191,0.000004481562,0.000006312297,0.003757647],"genre_scores_gemma":[0.9900692,0.009457473,0.00003398468,0.00005988162,0.0001507984,0.0000175162,0.000001094728,0.00001453045,0.0001955572],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04953513,"threshold_uncertainty_score":0.5637468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009318251406903982,"score_gpt":0.1834982966327425,"score_spread":0.1741800452258385,"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."}}