{"id":"W4387735364","doi":"10.22541/essoar.169766272.22238694/v1","title":"Addressing lighting and bounding box accuracy for the Embedded Automated Generator of Labeled Images (EAGL-I) system","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; University of Winnipeg","funders":"","keywords":"Minimum bounding box; Computer science; Bounding overwatch; Artificial intelligence; Generator (circuit theory); Computer vision; Segmentation; Noise (video); Black box; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003547722,0.001687635,0.0007452882,0.0009358507,0.0009042929,0.002443861,0.002905968,0.001592051,0.006982944],"category_scores_gemma":[0.02147164,0.0009154449,0.0006843376,0.0007251684,0.0008688209,0.002349813,0.002646991,0.002332425,0.002088965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002068487,"about_ca_system_score_gemma":0.001867025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008004035,"about_ca_topic_score_gemma":0.00981508,"domain_scores_codex":[0.9966475,0.0007016936,0.0001946891,0.0009200913,0.001216226,0.000319732],"domain_scores_gemma":[0.9908173,0.005046648,0.0005244312,0.001547555,0.001766108,0.0002980085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002030251,0.0004214306,0.01328218,0.0008726114,0.0001969672,0.0008747194,0.0008904269,0.1673983,0.1088211,0.008890201,0.04420439,0.6521174],"study_design_scores_gemma":[0.0001649817,0.0003314127,0.004331025,0.0001145352,0.00008200513,0.0004970569,0.0002380031,0.7742382,0.1955185,0.006627978,0.01769986,0.000156455],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1810548,0.0008671486,0.7266608,0.001851542,0.0006268414,0.0004401689,0.001615277,0.07890618,0.007977151],"genre_scores_gemma":[0.4609802,0.000223237,0.5269236,0.0005982268,0.0001024255,0.0002346174,0.002043831,0.006184353,0.002709567],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008004035,"threshold_uncertainty_score":0.02336031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09382182937782989,"score_gpt":0.3082579016184797,"score_spread":0.2144360722406498,"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."}}