{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001518857,0.001915074,0.001007075,0.003156307,0.0006374907,0.001691935,0.003388165,0.001914403,0.01874935],"category_scores_gemma":[0.008191844,0.000483389,0.001427225,0.007417116,0.0003580519,0.002139218,0.001575259,0.001828741,0.02289583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002089869,"about_ca_system_score_gemma":0.002096976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05368771,"about_ca_topic_score_gemma":0.0460017,"domain_scores_codex":[0.9986976,0.0002369872,0.0001784066,0.0003880745,0.000334052,0.0001646919],"domain_scores_gemma":[0.9966233,0.0008048099,0.0002592044,0.0007899121,0.001301198,0.0002215914],"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":[0.0001352006,0.00006655159,0.003414124,0.0003579296,0.00006266174,0.00003995235,0.00002480688,0.006123071,0.0003701127,0.000867737,0.9774871,0.01105072],"study_design_scores_gemma":[0.0006314162,0.0001291462,0.03387353,0.0003785566,0.00008696189,0.0001454876,0.0003113021,0.05152673,0.002805045,0.006539694,0.9034022,0.0001698983],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00165925,0.00009179305,0.0007719985,0.00017581,0.00005179092,0.00003537446,0.9945076,0.001733828,0.0009726127],"genre_scores_gemma":[0.001904918,0.00004319564,0.001363919,0.00004599999,0.00000869307,0.00008273233,0.9961265,0.0001063389,0.0003177561],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05368771,"threshold_uncertainty_score":0.1067504,"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."}}