{"id":"W4308065362","doi":"10.48550/arxiv.2111.14671","title":"ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative\\n Transfer in Weather and Climate Models","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Benchmarking; Computer science; Climate model; Inference; Radiative transfer; Computation; Subroutine; Machine learning; Artificial neural network; Numerical weather prediction; Meteorology; Artificial intelligence; Climate change; Algorithm; Geography","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008398249,0.0005703328,0.0008647644,0.00008401967,0.0005359989,0.0001935461,0.0004983022,0.0004613492,0.002507488],"category_scores_gemma":[0.0000668159,0.0006001275,0.0002532158,0.0007172808,0.0002736361,0.0008315668,0.0002189911,0.0006207141,0.0000209343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004790838,"about_ca_system_score_gemma":0.0001341365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007541719,"about_ca_topic_score_gemma":0.002695429,"domain_scores_codex":[0.9960576,0.0005376361,0.0006082274,0.001755587,0.0001192011,0.0009216891],"domain_scores_gemma":[0.9975564,0.001182817,0.0001730464,0.0006070234,0.00008758956,0.0003930631],"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":[0.0003421399,0.00009990198,0.1124834,0.0001808413,0.00009110965,0.00009866099,0.0007934928,0.8812937,0.000006276096,0.003237316,0.00001607564,0.001357101],"study_design_scores_gemma":[0.001639328,0.0002192891,0.04118605,0.00009923008,0.0002011982,0.000002240079,0.0008963526,0.9446438,0.000001071429,0.01000012,0.0004629683,0.0006483844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9465503,0.0009717798,0.04263283,0.00005889099,0.0002534282,0.001147567,0.006414718,0.00002441766,0.001946087],"genre_scores_gemma":[0.9891312,0.002685918,0.001866022,0.0002012529,0.00006689692,0.000002200011,0.005892417,0.00001610522,0.0001379659],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07129731,"threshold_uncertainty_score":0.999645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09236347743926014,"score_gpt":0.197031169159951,"score_spread":0.1046676917206909,"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."}}