{"id":"W4289356658","doi":"10.15258/sst.2022.50.1.s.05","title":"Automated seed identification with computer vision: challenges and opportunities","year":2022,"lang":"en","type":"article","venue":"Seed Science and Technology","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Food Inspection Agency","funders":"","keywords":"Identification (biology); Artificial intelligence; Computer science; Machine learning; Economic shortage; Machine vision; Automation; Engineering; 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":[0.0003470282,0.00008318118,0.0001010073,0.00006372866,0.0008006243,0.00006671578,0.0002327186,0.00004422521,0.00001467213],"category_scores_gemma":[0.000007747793,0.00003029183,0.000007370962,0.000645238,0.0005995721,0.0001858233,0.0002685519,0.0001029731,0.000001931443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001404451,"about_ca_system_score_gemma":0.00001527894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001185851,"about_ca_topic_score_gemma":0.00004732337,"domain_scores_codex":[0.999114,0.00002127311,0.00009598687,0.0003287297,0.0002445165,0.0001955191],"domain_scores_gemma":[0.9997044,0.00002705401,0.00005594913,0.00005335139,0.0001079345,0.00005136775],"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":[0.00002578917,0.0001165013,0.005019682,0.000009729181,0.00001379308,0.00004141267,0.0006257188,0.00000323733,0.4877445,0.02478009,0.0006814239,0.4809381],"study_design_scores_gemma":[0.000308533,0.002348787,0.8973573,0.00001930665,0.00001811203,0.0006357869,0.01501491,0.002201824,0.00319344,0.002484024,0.07600243,0.0004155085],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9754099,0.0009253244,6.964955e-7,0.02278789,0.00006677586,0.000112573,0.000004841624,0.0003576777,0.0003343601],"genre_scores_gemma":[0.999216,0.0002514989,0.00005461074,0.0003101895,0.00003329706,0.00002433521,0.000006905304,4.532705e-7,0.0001027387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8923377,"threshold_uncertainty_score":0.6157836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02202382315554214,"score_gpt":0.2138819778464361,"score_spread":0.191858154690894,"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."}}