{"id":"W4408364771","doi":"10.5194/essd-2025-83","title":"CY-Bench: A comprehensive benchmark dataset for sub-national crop yield forecasting","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Remote Sensing and Land Use","field":"Earth and Planetary Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"HORIZON EUROPE Digital, Industry and Space","keywords":"Benchmark (surveying); Yield (engineering); Crop; Agricultural engineering; Environmental science; Engineering; Geography; Forestry; Cartography; Materials 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":[0.0002809396,0.0002959338,0.0003608954,0.0001678944,0.0002578736,0.0002025596,0.0003380251,0.0002680158,0.0008904385],"category_scores_gemma":[0.0002806412,0.000236288,0.0001545812,0.0001187974,0.00005808745,0.00007965619,0.0001051079,0.0003931372,0.00004181397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008580377,"about_ca_system_score_gemma":0.0003404527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00444252,"about_ca_topic_score_gemma":0.005329047,"domain_scores_codex":[0.9982538,0.00005266959,0.0003699231,0.0006062492,0.0003487552,0.0003685729],"domain_scores_gemma":[0.9979656,0.001179579,0.0001600159,0.0003298339,0.0002449865,0.0001199952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001855919,0.00003866573,0.007120978,0.000678028,0.0002516923,0.00002909566,0.0001975778,0.09333503,0.0000150338,0.0001695346,0.7659471,0.1320317],"study_design_scores_gemma":[0.0004612472,0.0001076906,0.01690882,0.0003941141,0.00009805077,0.00003108482,0.0001087484,0.7546961,0.0001254463,0.006897351,0.2194473,0.0007241084],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2950681,0.003429993,0.01583812,0.005099547,0.01220895,0.004661862,0.3103129,0.0004880768,0.3528925],"genre_scores_gemma":[0.5920753,0.0004351763,0.05103033,0.007417255,0.00207046,0.000006625381,0.3415123,0.00002034139,0.005432179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.661361,"threshold_uncertainty_score":0.9749677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1108729015104403,"score_gpt":0.2862418928305192,"score_spread":0.1753689913200789,"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."}}