{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01158131,0.0006873069,0.0009730922,0.0006750131,0.0009153438,0.002540638,0.003859825,0.0002813695,0.0002058723],"category_scores_gemma":[0.001602546,0.0005975357,0.0005146188,0.0007166261,0.000131277,0.0003667198,0.01338128,0.0009921762,0.002828741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001269124,"about_ca_system_score_gemma":0.0000934091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003762561,"about_ca_topic_score_gemma":0.0004046154,"domain_scores_codex":[0.991199,0.0003157984,0.00149523,0.003171132,0.00224956,0.001569346],"domain_scores_gemma":[0.9933876,0.0007715024,0.001057589,0.00408638,0.0003149775,0.0003819015],"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":[0.00009607519,0.0003257613,0.005268718,0.0002286971,0.00006662718,0.00002222287,0.0013597,0.03164373,0.00003023024,0.0003095648,0.9582622,0.002386452],"study_design_scores_gemma":[0.0007887294,0.00003376382,0.0005143864,0.0001684174,0.00004395687,0.00000278405,0.0003026647,0.6897525,0.00001947973,0.002547711,0.3053457,0.0004798149],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0690517,0.001053175,0.4642952,0.01158948,0.02325243,0.004981388,0.4209607,0.002595142,0.002220736],"genre_scores_gemma":[0.2856024,0.002160684,0.07610099,0.00484621,0.002435341,0.00124032,0.5005322,0.00109012,0.1259918],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.6581088,"threshold_uncertainty_score":0.9996476,"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."}}