{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000625787,0.000116511,0.000260484,0.000006889838,0.00006677702,0.00001422129,0.0002071634,0.00002976371,0.003201095],"category_scores_gemma":[0.00005668146,0.00009153887,0.00009183021,0.00009922466,0.00005879291,0.0001040195,0.0001420331,0.00007490037,0.001795997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005605208,"about_ca_system_score_gemma":0.000001714542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001514729,"about_ca_topic_score_gemma":0.0001406396,"domain_scores_codex":[0.9990878,0.00008208548,0.0002155523,0.000249315,0.0001553723,0.0002098498],"domain_scores_gemma":[0.9994286,0.00003895479,0.00005496733,0.0003932739,0.000003542917,0.00008071438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002956503,0.001081798,0.3480437,0.004570193,0.0000767234,0.00001109204,0.002041227,0.01057303,0.0009227348,0.01018455,0.09158868,0.5308767],"study_design_scores_gemma":[0.0001686604,0.00003543549,0.008293903,0.0007846084,0.00004167214,0.000002760721,0.000004471658,0.01447017,0.00002392977,0.001923081,0.9740312,0.000220127],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2403026,0.01890942,0.001607484,0.001930024,0.0001934708,0.001012941,0.0000075429,0.0001721481,0.7358644],"genre_scores_gemma":[0.9881951,0.004972731,0.001478462,0.003883165,0.00005128423,0.00006981485,0.00001137365,0.00002770814,0.001310384],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8824425,"threshold_uncertainty_score":0.9989812,"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."}}