{"id":"W2521147242","doi":"10.1002/for.2439","title":"Benchmark Forecast and Error Modeling","year":2016,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Benchmarking; Benchmark (surveying); Computer science; Autoregressive model; Process (computing); Regression; Regression analysis; Software; Data mining; Econometrics; Machine learning; Statistics; Mathematics; 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":[0.0008578655,0.0001075253,0.0003382506,0.0002208685,0.00007813338,0.00003964419,0.0001201573,0.00005658341,0.0002233715],"category_scores_gemma":[0.0002965093,0.00008253261,0.0001137261,0.00005091658,0.00003103944,0.0005786589,0.00003392666,0.0001042743,0.00003049043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006124981,"about_ca_system_score_gemma":0.00001023644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003838427,"about_ca_topic_score_gemma":0.000004977911,"domain_scores_codex":[0.9987679,0.00000748747,0.0008086427,0.0001357529,0.00002365618,0.0002565745],"domain_scores_gemma":[0.9990059,0.00008749006,0.0006578747,0.0001001372,0.00001899654,0.0001296425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006794821,0.0002505016,0.5072667,0.0002607932,0.001028612,0.0001759876,0.006156014,0.05079469,0.000860501,0.06150021,0.00757149,0.363455],"study_design_scores_gemma":[0.002378225,0.0004635627,0.004556981,0.0003253682,0.00002465434,0.001148191,0.0001913115,0.8690869,0.0001141568,0.1129172,0.008299438,0.0004940748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9760243,0.0009835334,0.01667702,0.0008274468,0.0003171636,0.00003990139,0.00002467722,0.000004964052,0.005101027],"genre_scores_gemma":[0.9959554,0.0001161579,0.003216925,0.00009419434,0.000390413,6.34216e-7,3.241965e-7,0.00001433943,0.0002116038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8182921,"threshold_uncertainty_score":0.3365582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1954053801729682,"score_gpt":0.2359680379271932,"score_spread":0.04056265775422502,"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."}}