{"id":"W6911479108","doi":"10.5281/zenodo.11502142","title":"CY-Bench: A comprehensive benchmark dataset for subnational crop yield forecasting","year":2025,"lang":"en","type":"dataset","venue":"Socio-Environmental Systems Modeling","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Benchmark (surveying); Yield (engineering); Agriculture; Crop yield; Food security; Identification (biology)","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":["metaepi_narrow","sts"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.001056118,0.001497813,0.001653589,0.0005695467,0.001479756,0.0004255559,0.001508668,0.001290207,0.0003656842],"category_scores_gemma":[0.0002386166,0.00167368,0.0006502106,0.0002606841,0.0003126267,0.0005734925,0.001230702,0.001314311,0.0003772893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002965709,"about_ca_system_score_gemma":0.0003392967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001835493,"about_ca_topic_score_gemma":0.00001787875,"domain_scores_codex":[0.9921703,0.0003481829,0.002082534,0.002145068,0.001780785,0.001473088],"domain_scores_gemma":[0.9954516,0.001113366,0.00128425,0.001707325,0.00008891404,0.0003545713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001042905,0.0002253507,0.0001075746,0.001258513,0.0006074886,0.00002772997,0.00008427965,0.1111912,0.0002647759,0.00002190388,0.8860631,0.00004379448],"study_design_scores_gemma":[0.001359722,0.0001057076,0.000002110941,0.00124142,0.0007377079,0.00006726403,0.00905706,0.2364819,0.000001775155,0.0000969942,0.7492595,0.001588779],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001635506,0.002924726,0.00385509,0.00005528631,0.00200322,0.004039614,0.9853357,0.0001035591,0.00004729516],"genre_scores_gemma":[0.01249126,0.0001722687,0.0005891063,0.0002775469,0.001247239,0.001472758,0.9833497,0.0001911176,0.000209033],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1368036,"threshold_uncertainty_score":0.9998202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0785884097415409,"score_gpt":0.2865009370044917,"score_spread":0.2079125272629508,"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."}}