{"id":"W2156892295","doi":"10.5194/gmd-5-819-2012","title":"Towards a public, standardized, diagnostic benchmarking system for land surface models","year":2012,"lang":"en","type":"article","venue":"Geoscientific model development","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":124,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Lawrence Berkeley National Laboratory; Biological and Environmental Research; Natural Sciences and Engineering Research Council of Canada; Oak Ridge National Laboratory; University of New South Wales; Microsoft Research; Canadian Foundation for Climate and Atmospheric Sciences; Natural Resources Canada; Université Laval; U.S. Department of Energy; National Science Foundation","keywords":"Benchmarking; A priori and a posteriori; Computer science; Protocol (science); Work (physics); Business; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.00194672,0.0002474512,0.0002472968,0.0000627937,0.0006623843,0.0002075251,0.0003156679,0.00007838173,0.0001405236],"category_scores_gemma":[0.0001160083,0.0002289637,0.00006675899,0.0002653991,0.00009883103,0.000452681,0.0003930246,0.00008427454,0.00009787455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000649164,"about_ca_system_score_gemma":0.0001548995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001478304,"about_ca_topic_score_gemma":0.00009791416,"domain_scores_codex":[0.9972254,0.00003614521,0.0004295443,0.000549635,0.0007501831,0.001009103],"domain_scores_gemma":[0.9989669,0.0001368527,0.0001324952,0.0003329535,0.00005687678,0.0003739539],"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":[0.00008247011,0.0005902892,0.05415165,0.0005893864,0.000154802,0.00001102284,0.01338722,0.684529,0.001464171,0.01571615,0.04773623,0.1815876],"study_design_scores_gemma":[0.000714814,0.00001494267,0.004366998,0.00007283628,0.00002947592,0.000009201176,0.0002186997,0.9165305,0.0004668091,0.001121106,0.0758651,0.0005895218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1938616,0.0001022872,0.7977016,0.00006413741,0.001297953,0.0006285403,0.0001719656,0.00009615828,0.006075726],"genre_scores_gemma":[0.8166806,0.000008701643,0.1816079,0.00005237561,0.0000458126,0.0001550248,0.0001206658,0.0000249841,0.001304054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6228189,"threshold_uncertainty_score":0.9336867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03648892098034696,"score_gpt":0.2361041233209256,"score_spread":0.1996152023405786,"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."}}