{"id":"W3003709258","doi":"10.1029/2020ms002203","title":"WeatherBench: A Benchmark Data Set for Data‐Driven Weather Forecasting","year":2020,"lang":"en","type":"article","venue":"Journal of Advances in Modeling Earth Systems","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":445,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Seventh Framework Programme; Deutsche Forschungsgemeinschaft","keywords":"Benchmark (surveying); Set (abstract data type); Data set; Weather forecasting; Baseline (sea); Numerical weather prediction; Deep learning; Code (set theory); Simple (philosophy)","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":[0.001210144,0.0001344785,0.0003913146,0.00007560874,0.00009926341,0.00007936182,0.001043685,0.0000582334,0.0001044612],"category_scores_gemma":[0.0005449032,0.00009613432,0.00004944966,0.0001892616,0.00002546358,0.001368107,0.00005967691,0.0002231504,0.000006744251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003194369,"about_ca_system_score_gemma":0.00006203263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007002399,"about_ca_topic_score_gemma":0.000218683,"domain_scores_codex":[0.9981862,0.0001163317,0.0007929307,0.0003179955,0.0003221864,0.0002643609],"domain_scores_gemma":[0.9985148,0.0004562487,0.0003761748,0.0003951252,0.00009635185,0.0001613336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008704449,0.000007663642,0.01767574,0.00005980681,0.00001654752,0.00001026544,0.0002285539,0.9750401,0.00000747585,0.00002382836,0.00007964801,0.006763285],"study_design_scores_gemma":[0.0004585502,0.000241847,0.000130474,0.0001016076,0.00002027993,0.00001874197,0.0003999264,0.9847926,3.014444e-7,0.0005627681,0.01315705,0.000115825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3520347,0.03362061,0.6065868,0.0007636464,0.001867784,0.0009282637,0.00155521,0.00003796359,0.002605013],"genre_scores_gemma":[0.9748573,0.0003310826,0.02371269,0.0001235109,0.0007190067,6.064613e-7,0.0002371092,0.000005668532,0.0000130281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6228226,"threshold_uncertainty_score":0.3920244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2384365425349394,"score_gpt":0.3205473835112972,"score_spread":0.08211084097635782,"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."}}