{"id":"W2037943081","doi":"10.1175/2008waf2222130.1","title":"Evaluation of Probabilistic Medium-Range Temperature Forecasts from the North American Ensemble Forecast System","year":2008,"lang":"en","type":"article","venue":"Weather and Forecasting","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Hydro (Canada)","funders":"","keywords":"Consensus forecast; Forecast skill; Forecast period; Probabilistic logic; Statistics; Ensemble forecasting; Forecast verification; Econometrics; Environmental science; Brier score; Climatology; Meteorology; Mathematics; Economics; Geography; Production (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":[0.0008336388,0.0001415529,0.000246138,0.00003223267,0.000368332,0.00002336928,0.0001337084,0.00004009478,0.0001612299],"category_scores_gemma":[0.0003029222,0.00008099146,0.00005642817,0.0002712956,0.0002287976,0.00009540192,0.00001329723,0.0001242534,0.000008373677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009102345,"about_ca_system_score_gemma":0.0000512106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001602181,"about_ca_topic_score_gemma":0.006591976,"domain_scores_codex":[0.9984593,0.0002561417,0.0002998487,0.0002449799,0.0005170957,0.0002225661],"domain_scores_gemma":[0.9987251,0.0006546062,0.0001766182,0.0001775517,0.0001803954,0.00008569235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003852471,0.00001196812,0.9093914,0.00001537924,0.0000371016,0.000003205944,0.001504472,0.01186813,0.00003181689,0.00003600142,0.00003546575,0.07702652],"study_design_scores_gemma":[0.0002842832,0.000122243,0.7944594,0.00001976899,0.00007668215,0.00001775184,0.0003901188,0.2040442,0.00000708909,0.0004463315,0.00003406,0.00009805474],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933769,0.0005794152,0.00007345027,0.00004919906,0.0001001427,0.000383032,0.0001294112,0.00002723201,0.005281292],"genre_scores_gemma":[0.9991486,0.00001191683,0.0004920085,0.00004958452,0.0001834203,0.000007078358,0.00008135824,0.000005007841,0.00002101518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1921761,"threshold_uncertainty_score":0.3678477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0709701141097742,"score_gpt":0.2319312072720505,"score_spread":0.1609610931622762,"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."}}