{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001295128,0.001999486,0.0007719057,0.001596382,0.0010439,0.001502579,0.003634244,0.001988876,0.006038051],"category_scores_gemma":[0.005060385,0.0006294355,0.001701724,0.002913975,0.000748054,0.001269757,0.001400487,0.002254354,0.006098414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002145627,"about_ca_system_score_gemma":0.003203689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2249094,"about_ca_topic_score_gemma":0.359872,"domain_scores_codex":[0.9990829,0.0001758096,0.00008933745,0.000262135,0.0002681442,0.000121733],"domain_scores_gemma":[0.9985001,0.0003697688,0.00009148186,0.0004316122,0.0004351584,0.0001718291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002161822,0.0002093987,0.01305197,0.0006326974,0.0002723815,0.0001471938,0.0001146051,0.05766579,0.001053003,0.002554302,0.9086786,0.01540392],"study_design_scores_gemma":[0.0007817041,0.0001241965,0.04358872,0.0002776965,0.0001357372,0.0002405561,0.0003710713,0.3050627,0.005935952,0.007857513,0.6354304,0.0001937049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03282122,0.0008582143,0.0071688,0.001058275,0.0003878576,0.0001731877,0.9335877,0.01630536,0.007639474],"genre_scores_gemma":[0.02398355,0.0002024641,0.008339914,0.0001695585,0.00004403279,0.0001538127,0.96495,0.0009815106,0.001175286],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2249094,"threshold_uncertainty_score":0.4472005,"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."}}