{"id":"W1766891869","doi":"10.1002/met.1392","title":"Progress and challenges in forecast verification","year":2013,"lang":"en","type":"article","venue":"Meteorological Applications","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Computer science; Data assimilation; Forecast verification; Variety (cybernetics); Data science; Meteorology; Forecast skill; Artificial intelligence; Geography","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002235155,0.0001055268,0.0001521298,0.00006954162,0.0001171063,0.00004317363,0.0001534621,0.00009773076,0.002092415],"category_scores_gemma":[0.00003613174,0.00007377316,0.00002428835,0.0002200879,0.0001773098,0.0001499012,0.00001460461,0.0001165951,0.0004455652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003129482,"about_ca_system_score_gemma":0.000005389121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008052669,"about_ca_topic_score_gemma":0.0001175453,"domain_scores_codex":[0.9990087,0.0000872907,0.0002254932,0.0003359605,0.0001051052,0.0002374199],"domain_scores_gemma":[0.9993532,0.000249968,0.00004980488,0.0001906001,0.00003270927,0.0001236995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000008045522,0.00006614892,0.2583652,0.00001245213,0.000005088537,5.983832e-7,0.00006060409,0.0002598016,0.00003981755,0.01871771,0.00002091351,0.7224436],"study_design_scores_gemma":[0.0001319183,0.00009183275,0.9093034,0.000001239739,0.000003949046,0.000002459615,0.0000593152,0.009937784,0.000004011348,0.06757348,0.01279301,0.00009755376],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9537551,0.009360984,0.001097388,0.008599305,0.00003232695,0.001618088,0.00002166962,0.0001350452,0.02538012],"genre_scores_gemma":[0.9940366,0.0008254711,0.004558882,0.0001712927,0.00003938037,0.0002845683,0.00005290021,0.000001979708,0.00002897602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7223461,"threshold_uncertainty_score":0.9988198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07775056215445175,"score_gpt":0.2425196618618578,"score_spread":0.164769099707406,"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."}}