{"id":"W4407062605","doi":"10.1016/j.eja.2025.127528","title":"CSWin-MBConv: A dual-network fusing CNN and Transformer for weed recognition","year":2025,"lang":"en","type":"article","venue":"European Journal of Agronomy","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"National Key Research and Development Program of China; Earmarked Fund for Modern Agro-industry Technology Research System; National Natural Science Foundation of China","keywords":"Weed; Transformer; Dual (grammatical number); Artificial intelligence; Computer science; Agronomy; Mathematics; Biology; Engineering; Linguistics","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":[0.0005325162,0.00009959711,0.0001585718,0.00001394653,0.0001755366,0.00008094862,0.00008377467,0.00002276823,0.00007635246],"category_scores_gemma":[0.00001892143,0.00003534281,0.000125249,0.000148954,0.00002868863,0.0001645516,0.00001239423,0.0001050748,0.000008765138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001005836,"about_ca_system_score_gemma":0.000007660734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004600848,"about_ca_topic_score_gemma":0.00001426922,"domain_scores_codex":[0.9992542,0.0001031161,0.0002991009,0.0001122765,0.00006373389,0.0001675167],"domain_scores_gemma":[0.9995403,0.0001346833,0.0001379713,0.0000170346,0.0001030419,0.00006691849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002018863,0.00007356321,0.001482404,0.00002050412,0.0001223371,0.00002267364,0.000228178,0.00001123473,0.08002846,0.0001461278,0.04345769,0.8742049],"study_design_scores_gemma":[0.001058077,0.0006774163,0.2415275,0.0003621497,0.0001417252,0.00007356699,0.0006756572,0.000005712882,0.002831192,0.00123921,0.7511531,0.0002547283],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9820925,0.0007999815,0.0003412976,0.003117324,0.0002927353,0.0002048047,0.00000601477,0.00001325607,0.01313208],"genre_scores_gemma":[0.9957076,0.00006638825,0.001391928,0.0006293851,0.001488579,0.0000028444,0.0000177492,0.000001260026,0.0006942683],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8739502,"threshold_uncertainty_score":0.1441238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647615347823669,"score_gpt":0.1966442443746263,"score_spread":0.1801680908963896,"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."}}