{"id":"W3190594171","doi":"10.48550/arxiv.2108.05789","title":"Presenting an extensive lab- and field-image dataset of crops and weeds for computer vision tasks in agriculture","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Sample (material); Metadata; Computer science; Field (mathematics); Variety (cybernetics); Artificial intelligence; Filter (signal processing); Perspective (graphical); Point (geometry); Computer vision; Mathematics; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0006979629,0.002245365,0.001327346,0.004598104,0.001023558,0.001715308,0.002342016,0.002259713,0.01237245],"category_scores_gemma":[0.002063099,0.0005542701,0.001783194,0.005130338,0.0005140616,0.001773652,0.001937134,0.00153525,0.0180168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001399717,"about_ca_system_score_gemma":0.001354454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02184536,"about_ca_topic_score_gemma":0.08272146,"domain_scores_codex":[0.998255,0.0001720932,0.0001618968,0.0005682403,0.0005901935,0.0002526243],"domain_scores_gemma":[0.9987432,0.000225524,0.0000909189,0.0003800866,0.0004000607,0.0001602065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004806455,0.0007139849,0.005926862,0.004105809,0.0002818706,0.0005629402,0.0002194945,0.004945585,0.01287505,0.001033862,0.8454813,0.1233725],"study_design_scores_gemma":[0.0002051368,0.000303956,0.05651785,0.0008616734,0.0001491802,0.00160354,0.0008485928,0.01645781,0.01509849,0.002463921,0.9052922,0.0001976321],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02097046,0.004067376,0.01156293,0.0006530743,0.0006032943,0.0005417107,0.9393376,0.0114774,0.01078616],"genre_scores_gemma":[0.009723766,0.0006753675,0.01401899,0.0001856457,0.00005517872,0.0001908679,0.972849,0.0002635338,0.002037726],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02184536,"threshold_uncertainty_score":0.04343641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04033155243040285,"score_gpt":0.1963444702294847,"score_spread":0.1560129177990819,"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."}}