{"id":"W4410079886","doi":"10.1016/j.eja.2025.127659","title":"Evaluating the AgMIP calibration protocol for crop models; case study and new diagnostic tests","year":2025,"lang":"en","type":"article","venue":"European Journal of Agronomy","topic":"Crop Yield and Soil Fertility","field":"Agricultural and Biological Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"BonaRes; Bundesanstalt für Landwirtschaft und Ernährung; Bundesamt für Landwirtschaft; Bundesministerium für Bildung und Frauen; Rural Development Administration; Bundesministerium für Bildung und Forschung; Bundesministerium für Ernährung und Landwirtschaft; Deutsche Forschungsgemeinschaft; Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement; Ministerstvo Školství, Mládeže a Tělovýchovy; European Commission","keywords":"Calibration; Agronomy; Protocol (science); Crop; Environmental science; Mathematics; Biology; Statistics; Medicine","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":[0.001118846,0.00007729125,0.0001039236,0.000008177824,0.0002576216,0.0001453853,0.0001381851,0.00001014403,0.00002479738],"category_scores_gemma":[0.0003152986,0.00002372728,0.00005665375,0.00008257027,0.00002638621,0.0001536042,0.00005445976,0.00009877297,5.485823e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001018759,"about_ca_system_score_gemma":0.00002834616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008944499,"about_ca_topic_score_gemma":0.0001489941,"domain_scores_codex":[0.9990628,0.000330636,0.0003109385,0.0001124513,0.00008696826,0.00009616758],"domain_scores_gemma":[0.9988663,0.0007947792,0.0001477482,0.00004207737,0.00008939292,0.00005969596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000401839,0.000408964,0.0187641,0.00003047879,0.0000663879,0.0003026875,0.00216542,0.000876875,0.002556338,0.0001061946,0.005189952,0.9691308],"study_design_scores_gemma":[0.005212572,0.008938264,0.9424013,0.0003584307,0.0002247888,0.0007379179,0.009015569,0.01251912,0.000292492,0.004035671,0.01580771,0.0004560948],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9832889,0.00003152157,0.0003001856,0.001122918,0.00003903898,0.01472015,0.000001166216,0.000006964709,0.0004890984],"genre_scores_gemma":[0.9984964,4.985735e-7,0.0002258585,0.0001095453,0.0001862182,0.0007563637,4.527294e-7,7.270921e-7,0.0002238968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9686747,"threshold_uncertainty_score":0.1981443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1663999068538765,"score_gpt":0.3651061404348238,"score_spread":0.1987062335809473,"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."}}