{"id":"W4401997064","doi":"10.2139/ssrn.4939059","title":"Using Soft-Nms and Mask-Scoring R-Cnn to Improve the Detection of Overlapping Insects","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Insect Resistance and Genetics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology)","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":[0.0007841229,0.0002437942,0.0002150084,0.0001035536,0.0001563002,0.00008923109,0.0002513975,0.0002691836,9.837361e-7],"category_scores_gemma":[0.00004717267,0.0001963525,0.0001609731,0.0001005662,0.00005066789,0.000002633418,0.0004463433,0.001782127,0.000001379377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002484107,"about_ca_system_score_gemma":0.001357944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008524927,"about_ca_topic_score_gemma":0.0008715743,"domain_scores_codex":[0.9980635,0.00006329786,0.0003178125,0.0003796749,0.0001909089,0.0009847982],"domain_scores_gemma":[0.9993057,0.00001039352,0.0002098476,0.0003148271,0.00009830312,0.00006095936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000104122,0.00001102374,0.00008060313,0.0001202027,0.0002934675,0.00000195149,0.0002187683,0.0009861257,0.9791996,0.0003355112,0.000004287771,0.01864437],"study_design_scores_gemma":[0.0008028272,0.001699311,0.0005719741,0.0006531572,0.0005461257,0.0008421873,0.00232483,0.001859369,0.8558136,0.131069,0.002773502,0.001044033],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9505916,0.02441928,0.02384836,0.00009026962,0.0007048864,0.0002372326,0.000007214268,0.000007434765,0.00009377921],"genre_scores_gemma":[0.9918119,0.006557303,0.0002047917,0.00006699806,0.000987641,0.000009589378,0.000003857161,0.00004448147,0.0003134105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1307335,"threshold_uncertainty_score":0.8007025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009248197614928,"score_gpt":0.254049793569569,"score_spread":0.244801595954641,"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."}}