{"id":"W4406487155","doi":"10.1016/j.compag.2025.109963","title":"Towards end-to-end rice row detection in paddy fields exploiting two-pathway instance segmentation","year":2025,"lang":"en","type":"article","venue":"Computers and Electronics in Agriculture","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Special Project for Research and Development in Key areas of Guangdong Province; National Natural Science Foundation of China","keywords":"End-to-end principle; Paddy field; Dead end; Segmentation; Computer science; Artificial intelligence; Computer vision; Mathematics; Agronomy; Geometry; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001951294,0.0002036147,0.0002189168,0.00004404867,0.0001639589,0.0001169589,0.0001886547,0.0001551787,0.000009537056],"category_scores_gemma":[0.00001850842,0.00008436109,0.0000547596,0.001177076,0.00001578293,0.000179675,0.00008917345,0.0003680416,0.000002482948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552357,"about_ca_system_score_gemma":0.00001569674,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004155182,"about_ca_topic_score_gemma":0.01839654,"domain_scores_codex":[0.9986777,0.00007296327,0.0002642668,0.0004222566,0.0001533047,0.0004094758],"domain_scores_gemma":[0.9996771,0.00009813747,0.0000634964,0.00004588417,0.00004992808,0.00006549025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004322838,0.0001308069,0.003288652,0.00002525361,0.00001724027,0.00001197779,0.0006780404,0.0005415721,0.3974554,0.001710335,0.001746102,0.5943514],"study_design_scores_gemma":[0.002383136,0.001195289,0.6850194,0.0006850316,0.00004344354,0.00004629173,0.004312747,0.00207853,0.1801068,0.005902772,0.1166196,0.001606954],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938463,0.001169879,0.0006565141,0.002254002,0.000285202,0.0003373325,0.000005335583,0.00005648013,0.001388975],"genre_scores_gemma":[0.9978619,0.0002700948,0.000287282,0.001085027,0.0002227669,0.00005029374,0.00005014703,9.287702e-7,0.0001716221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6817307,"threshold_uncertainty_score":0.9995152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00745952144368215,"score_gpt":0.2143794201702743,"score_spread":0.2069198987265922,"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."}}