{"id":"W3153421944","doi":"10.3389/frobt.2021.627067","title":"Towards a Machine Vision-Based Yield Monitor for the Counting and Quality Mapping of Shallots","year":2021,"lang":"en","type":"article","venue":"Frontiers in Robotics and AI","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Mitacs","keywords":"Computer science; Machine vision; Artificial intelligence; Agricultural engineering; Python (programming language); Engineering","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":[0.0002450423,0.00007786103,0.0001685763,0.000006626392,0.0001264785,0.00005180407,0.00007195376,0.00005811163,0.000006560369],"category_scores_gemma":[0.00009477533,0.00002590626,0.00004610574,0.0001486249,0.00004572444,0.00003799262,0.0000420308,0.00007645667,6.154804e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005679713,"about_ca_system_score_gemma":0.000007200131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001779818,"about_ca_topic_score_gemma":0.0002745361,"domain_scores_codex":[0.9994228,0.00002502186,0.0001705556,0.0001576835,0.00009517006,0.0001287173],"domain_scores_gemma":[0.9995669,0.0002486258,0.0000557682,0.00003301725,0.00006410443,0.0000316422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008330482,0.0002375707,0.6956365,0.0002084226,0.00008216291,0.000006536474,0.0004032587,0.001336967,0.06633453,0.001397881,0.009209701,0.2250632],"study_design_scores_gemma":[0.0004408802,0.0001353844,0.9576076,0.0001741788,0.00003310435,0.00000205475,0.002101342,0.02381589,0.002766923,0.00120216,0.01147486,0.0002456587],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9487128,0.009433247,0.01260051,0.02768106,0.0008489421,0.0004201861,0.00009979647,0.00002337626,0.0001801283],"genre_scores_gemma":[0.9942824,0.0001805466,0.004698395,0.0005901098,0.0001423391,0.000006578798,0.00001916014,6.758085e-7,0.00007985318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2619711,"threshold_uncertainty_score":0.1056427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02884040106710604,"score_gpt":0.2546543891591448,"score_spread":0.2258139880920388,"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."}}