{"id":"W1964111098","doi":"10.1175/mwr-d-14-00045.1","title":"Comparing Forecast Skill","year":2014,"lang":"en","type":"article","venue":"Monthly Weather Review","topic":"Climate variability and models","field":"Environmental Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Aeronautics and Space Administration; U.S. Department of Energy","keywords":"Forecast skill; Econometrics; Statistics; Wilcoxon signed-rank test; Test (biology); Sample (material); Sign test; Statistical hypothesis testing; Sign (mathematics); Set (abstract data type); Mathematics; Computer science; Mann–Whitney U test","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008113123,0.0004098311,0.0008349324,0.00286256,0.0002307121,0.001617508,0.0007012967,0.0006916694,0.004969169],"category_scores_gemma":[0.05354514,0.0001409817,0.0005660467,0.002124274,0.0007650032,0.001775843,0.001116177,0.0008982705,0.001021471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008580752,"about_ca_system_score_gemma":0.0008938828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005178602,"about_ca_topic_score_gemma":0.003325426,"domain_scores_codex":[0.9959707,0.00129224,0.0002478312,0.000605425,0.001618563,0.000265297],"domain_scores_gemma":[0.9740431,0.01853214,0.002104741,0.001635926,0.003085424,0.0005987913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008011669,0.0001489454,0.3350706,0.001058879,0.001711562,0.0001402935,0.0007417151,0.09253747,0.002310799,0.03568937,0.026629,0.5031602],"study_design_scores_gemma":[0.0001463197,0.001076591,0.6931167,0.0006186683,0.0005573282,0.0002082331,0.001366796,0.1597977,0.004868536,0.09486999,0.04316926,0.0002038954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7692465,0.01751306,0.08748206,0.005579147,0.001507021,0.0002102386,0.006575692,0.0009508536,0.1109355],"genre_scores_gemma":[0.9906039,0.001576773,0.004256793,0.0001811097,0.0002457119,0.00002744782,0.001690405,0.00006104987,0.001356864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008113123,"threshold_uncertainty_score":0.04290682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03219450443075644,"score_gpt":0.249871878090689,"score_spread":0.2176773736599326,"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."}}