{"id":"W4317378137","doi":"10.1016/j.compag.2023.107623","title":"AutoOLA: Automatic object level augmentation for wheat spikes counting","year":2023,"lang":"en","type":"article","venue":"Computers and Electronics in Agriculture","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Millar College of the Bible; National Research Council Canada; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"National Research Council Canada","keywords":"Mean squared error; Mean absolute percentage error; Artificial intelligence; Computer science; Process (computing); Object (grammar); Pattern recognition (psychology); Field (mathematics); Statistics; Machine learning; Mathematics; Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002420032,0.0001976613,0.0002247753,0.000024841,0.0002803913,0.0001544184,0.0001690988,0.0001383431,0.000009875112],"category_scores_gemma":[0.00002012468,0.00007125823,0.00008630833,0.0007113417,0.00002034258,0.0001590627,0.00005889861,0.0001644394,0.00001066352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006546095,"about_ca_system_score_gemma":0.00001024735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005806833,"about_ca_topic_score_gemma":0.001116225,"domain_scores_codex":[0.9987287,0.00003261519,0.0002304576,0.0003525104,0.0001636816,0.0004920665],"domain_scores_gemma":[0.9995405,0.0002278411,0.00007592959,0.00003691428,0.00005646269,0.00006235845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00004165296,0.0001937941,0.01021502,0.0001658346,0.00007577863,0.00001603296,0.001232921,0.0006344743,0.4205993,0.005401589,0.2432383,0.3181853],"study_design_scores_gemma":[0.001641014,0.00104433,0.7496611,0.0003162241,0.00007754839,0.00006728155,0.001893964,0.02257611,0.006557159,0.005789743,0.2091016,0.001273914],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954353,0.0007646671,0.000146699,0.002439847,0.0002880557,0.0005026543,0.00002830802,0.0002378982,0.0001565725],"genre_scores_gemma":[0.9961396,0.0004568239,0.0006805077,0.0005166563,0.0006631745,0.0001061485,0.0006524738,0.000002543201,0.0007821114],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7394461,"threshold_uncertainty_score":0.2905826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02208010302096411,"score_gpt":0.2325246945924517,"score_spread":0.2104445915714876,"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."}}