{"id":"W4388514520","doi":"10.48550/arxiv.2311.03721","title":"ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning","year":2023,"lang":"en","type":"preprint","venue":"elib (German Aerospace Center)","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Environment Research Council; European Commission; Canadian Institute for Advanced Research","keywords":"Downscaling; Computer science; Emulation; Climate model; Climate change; Scale (ratio); Machine learning; Benchmark (surveying); Pipeline (software); Preprocessor; Modular design; Artificial intelligence; Data science; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001617253,0.001536059,0.0007503007,0.001606735,0.0008308883,0.001196946,0.003041537,0.002314273,0.006925121],"category_scores_gemma":[0.005630484,0.0005375665,0.001754113,0.003051487,0.000582118,0.001560874,0.001852699,0.002908744,0.006997911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001271492,"about_ca_system_score_gemma":0.002415977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01426102,"about_ca_topic_score_gemma":0.02744549,"domain_scores_codex":[0.9988475,0.000257146,0.0001538795,0.0003197659,0.000322213,0.00009953878],"domain_scores_gemma":[0.9978092,0.0005928396,0.0002015585,0.0007474916,0.0004125205,0.0002362793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003926493,0.0004461386,0.01481089,0.0009860076,0.0003185995,0.0002497818,0.0001408746,0.05243301,0.003608664,0.004614728,0.8938853,0.02811328],"study_design_scores_gemma":[0.001174579,0.0002076903,0.04387047,0.0002625402,0.0001323897,0.0003865863,0.0003449953,0.1597127,0.01062915,0.01663359,0.7663884,0.000256964],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0205932,0.0005205102,0.008532444,0.001291154,0.0003668896,0.0002035796,0.9547874,0.009767645,0.00393717],"genre_scores_gemma":[0.01905377,0.0001433152,0.01086157,0.0001815878,0.00005317444,0.0002697191,0.9682776,0.0004817446,0.0006776276],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01426102,"threshold_uncertainty_score":0.02835602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1657891308772633,"score_gpt":0.4265862715469295,"score_spread":0.2607971406696662,"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."}}