{"id":"W2094507162","doi":"10.1016/j.agsy.2014.01.008","title":"An evaluation of the statistical methods for testing the performance of crop models with observed data","year":2014,"lang":"en","type":"article","venue":"Agricultural Systems","topic":"Irrigation Practices and Water Management","field":"Agricultural and Biological Sciences","cited_by":346,"is_retracted":false,"has_abstract":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Statistics; Mathematics; Calibration; Mean squared error; Linear regression; Index (typography); Computer science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002784997,0.00007837822,0.0001255673,0.000002128428,0.0001946807,0.00005961654,0.0005389014,0.00002607252,0.000005216114],"category_scores_gemma":[0.0001410184,0.0000150856,0.00001939308,0.0001881755,0.00004502173,0.0003612242,0.00007935364,0.00004279091,4.152355e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001155715,"about_ca_system_score_gemma":0.000005937743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007290858,"about_ca_topic_score_gemma":0.00009045855,"domain_scores_codex":[0.9985066,0.0006282458,0.0002511195,0.0001776047,0.00032419,0.0001122365],"domain_scores_gemma":[0.9984607,0.0005779463,0.0003285697,0.0001695084,0.0004409262,0.00002232148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001216571,0.0002474703,0.01423458,0.0003566806,0.0001762724,5.171891e-8,0.0005271612,0.1132993,0.4814559,0.02352188,0.0009263615,0.3651327],"study_design_scores_gemma":[0.0001281049,0.0002909215,0.3201195,0.00004581265,0.0001112894,0.000002236386,0.0005486243,0.6766346,0.0009615007,0.0001838918,0.0009027309,0.00007089906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969221,0.0000391953,0.001447005,0.0003393508,0.0001152267,0.0007874522,0.00004396413,0.00001030838,0.0002954267],"genre_scores_gemma":[0.9965524,0.000001279317,0.003141316,0.00001225096,0.00008451204,0.0000498369,0.0001144767,5.827475e-7,0.00004333205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5633352,"threshold_uncertainty_score":0.1497346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2892124896802746,"score_gpt":0.3469581334243645,"score_spread":0.05774564374408991,"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."}}