{"id":"W3201404958","doi":"","title":"Learned Benchmarks for Subseasonal Forecasting.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Meteorological Phenomena and Simulations","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Precipitation; Climate Forecast System; Forecast skill; Quantitative precipitation forecast; Persistence (discontinuity); Range (aeronautics); Climatology; Meteorology; Machine learning; Madden–Julian oscillation; Artificial intelligence; Engineering; Convection; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00191572,0.001188928,0.0005129779,0.001115702,0.0004822086,0.001246595,0.002581145,0.0008084272,0.004864173],"category_scores_gemma":[0.01255604,0.0003544357,0.000517561,0.001750695,0.0004338432,0.002095956,0.001410594,0.001941298,0.001800085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001288755,"about_ca_system_score_gemma":0.002062327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03657182,"about_ca_topic_score_gemma":0.04138068,"domain_scores_codex":[0.9989415,0.0003273085,0.00008989533,0.0002036904,0.000333591,0.0001041163],"domain_scores_gemma":[0.9964837,0.001152238,0.0002216681,0.0009617197,0.0009625721,0.0002180775],"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":[0.0001671261,0.0001888319,0.01203393,0.0003182312,0.0001701301,0.00008620752,0.00007025835,0.8214896,0.0009809291,0.01567379,0.07986663,0.06895422],"study_design_scores_gemma":[0.00003731921,0.00004460991,0.001420175,0.00002875523,0.00001380534,0.00002039679,0.00003342234,0.9718979,0.00152384,0.01070577,0.01425567,0.00001836749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2301434,0.003439546,0.5495106,0.004794045,0.002271524,0.0005602925,0.07816432,0.05863896,0.07247738],"genre_scores_gemma":[0.6940688,0.0008981591,0.2024546,0.0005758239,0.000244096,0.0004959838,0.09369553,0.002459609,0.005107488],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03657182,"threshold_uncertainty_score":0.07271791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1843191915092604,"score_gpt":0.1982719276654063,"score_spread":0.01395273615614587,"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."}}