{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00557933,0.0008735944,0.0005715594,0.002490629,0.0007488485,0.003576834,0.0007675389,0.001254739,0.003585686],"category_scores_gemma":[0.04677423,0.0002015139,0.000454928,0.001511848,0.001937732,0.005669422,0.002262936,0.001778122,0.0005551052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007844499,"about_ca_system_score_gemma":0.0007344066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001583715,"about_ca_topic_score_gemma":0.001381165,"domain_scores_codex":[0.9969952,0.001397671,0.0001621833,0.0003977609,0.000896482,0.0001506108],"domain_scores_gemma":[0.9829577,0.007482594,0.004742283,0.001633218,0.001967986,0.001216244],"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":[0.000757757,0.0003913364,0.06343324,0.0002238434,0.0002211952,0.0002088674,0.002052728,0.0177253,0.002141092,0.6389877,0.01100315,0.2628539],"study_design_scores_gemma":[0.00005817232,0.0008125465,0.09355824,0.0002653227,0.00007652261,0.0001810507,0.001365142,0.0679874,0.001671512,0.8254192,0.008407159,0.0001977456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5850346,0.00385181,0.3138501,0.00842825,0.0006691554,0.0001496172,0.001137797,0.0003064043,0.08657222],"genre_scores_gemma":[0.9855781,0.000367818,0.01152017,0.0001779807,0.0001768874,0.00005544252,0.0001680751,0.0000437119,0.001911823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00557933,"threshold_uncertainty_score":0.02950668,"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."}}