{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1178144,0.001968796,0.001310367,0.002931066,0.001109788,0.00138296,0.003189323,0.001845536,0.001489648],"category_scores_gemma":[0.2504265,0.0005990914,0.002668907,0.002274591,0.002061246,0.002625344,0.002008457,0.00214721,0.0002459712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001702318,"about_ca_system_score_gemma":0.002681987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006884595,"about_ca_topic_score_gemma":0.004827227,"domain_scores_codex":[0.9234759,0.06695164,0.002226262,0.002437032,0.004444459,0.0004646848],"domain_scores_gemma":[0.3027655,0.6767418,0.005502863,0.008238095,0.006219116,0.0005326032],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005765794,0.001566609,0.09837662,0.001375402,0.00494305,0.0005119276,0.001005569,0.5755417,0.005100782,0.02761582,0.002864866,0.2753319],"study_design_scores_gemma":[0.0003411078,0.002343189,0.01037588,0.00009962804,0.0002978511,0.000230955,0.0002159,0.9743859,0.003076365,0.007727324,0.0008164441,0.00008946669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2223004,0.001033188,0.7724847,0.0004757539,0.0001396171,0.0004904422,0.0006732556,0.0009051768,0.001497535],"genre_scores_gemma":[0.6534684,0.0006306644,0.3427192,0.0001532533,0.0001121121,0.0008060907,0.00100394,0.0003176954,0.0007886742],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8821856,"threshold_uncertainty_score":0.6230697,"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."}}