{"id":"W2146676240","doi":"10.1002/qj.268","title":"Impact of observational error on the validation of ensemble prediction systems","year":2008,"lang":"en","type":"article","venue":"Quarterly Journal of the Royal Meteorological Society","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Brier score; Reliability (semiconductor); Observational study; Statistics; Receiver operating characteristic; Computer science; Histogram; Mathematics; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.001145854,0.0001220478,0.0003164191,0.00002161394,0.0002478337,0.00001392407,0.0003750525,0.0001211678,0.0006388683],"category_scores_gemma":[0.0001968832,0.00004910481,0.0006595586,0.0002029907,0.0002337759,0.00009995727,0.000006882058,0.0002954665,0.000005365343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001605868,"about_ca_system_score_gemma":0.00006389894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001114594,"about_ca_topic_score_gemma":0.000002047212,"domain_scores_codex":[0.9979334,0.0005251492,0.0006737189,0.0001092296,0.0005865854,0.0001718702],"domain_scores_gemma":[0.9976471,0.001130051,0.0007520681,0.0001789637,0.0002171188,0.00007466754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002019807,0.0001185998,0.5406796,0.000008108384,0.0001799899,0.000001047898,0.0004650937,0.4554706,0.0005059437,0.0003247359,0.001289391,0.0007548905],"study_design_scores_gemma":[0.0002921229,0.003623495,0.9511158,0.00001376087,0.00004408338,0.00001299321,0.0001324272,0.04212565,0.00006218675,0.002483411,0.00004141548,0.00005265552],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978513,0.0001721229,0.0006698261,0.000293021,0.0002989249,0.0001737244,0.00007103205,0.000006223022,0.0004638187],"genre_scores_gemma":[0.9994207,0.000008094681,0.0002836712,0.00007731131,0.0001414148,8.336812e-7,0.00000790479,0.000001980507,0.00005809051],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.413345,"threshold_uncertainty_score":0.6995159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07906041572139631,"score_gpt":0.262450098756735,"score_spread":0.1833896830353386,"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."}}