{"id":"W4412710017","doi":"10.21203/rs.3.rs-7030704/v1","title":"Automated Weed Segmentation: A Knowledge- Based Approach to Support Machine Learning Training","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Canada First Research Excellence Fund","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Precision agriculture; Workflow; Machine learning; Random forest; Bottleneck; Deep learning; Feature (linguistics); Pattern recognition (psychology); Database; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006173757,0.001140828,0.001236402,0.002438501,0.0008275278,0.001377375,0.003302966,0.002362191,0.007790029],"category_scores_gemma":[0.003322249,0.0008235807,0.001335417,0.001975751,0.0005628234,0.001775271,0.001617356,0.001564701,0.002627558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009804365,"about_ca_system_score_gemma":0.001724465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01676127,"about_ca_topic_score_gemma":0.02274867,"domain_scores_codex":[0.9994907,0.00005619915,0.00002998045,0.0002023442,0.0001399757,0.00008066079],"domain_scores_gemma":[0.9987533,0.0006027527,0.00008307028,0.0001924121,0.0003060092,0.00006244831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003038175,0.000407834,0.001664278,0.0001622915,0.00009286671,0.0002264588,0.0001275337,0.225028,0.01524336,0.004120958,0.009647002,0.7429757],"study_design_scores_gemma":[0.00001097862,0.0000218918,0.0002587905,0.000009608852,0.00001221609,0.00002265156,0.00001799076,0.9919693,0.002865545,0.003923179,0.0008808913,0.000006893363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0233417,0.0002021998,0.9635717,0.0002269973,0.00005875507,0.0001288585,0.0008513506,0.008185345,0.00343293],"genre_scores_gemma":[0.3678466,0.0001817218,0.6241853,0.000223451,0.0000744135,0.0002446777,0.002386812,0.0004680041,0.004389124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01676127,"threshold_uncertainty_score":0.0333274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1176442228009357,"score_gpt":0.3764688336085891,"score_spread":0.2588246108076534,"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."}}