{"id":"W4402905736","doi":"10.1167/jov.24.10.1523","title":"When Machines Outshine Humans in Object Recognition, Benchmarking Dilemma","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Currency Recognition and Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Benchmarking; Dilemma; Computer science; Artificial intelligence; Object (grammar); Psychology; Business; Philosophy; Epistemology","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":[0.0682693,0.001421034,0.002114507,0.003304781,0.002855754,0.01115874,0.004432014,0.007479781,0.005158977],"category_scores_gemma":[0.1949613,0.0008093544,0.0006497527,0.002397598,0.01786001,0.02622958,0.009562488,0.01151639,0.003449823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002283435,"about_ca_system_score_gemma":0.002711088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002208288,"about_ca_topic_score_gemma":0.002100965,"domain_scores_codex":[0.9527215,0.02688404,0.002082822,0.006849425,0.01011998,0.001342217],"domain_scores_gemma":[0.8888809,0.07245394,0.00415175,0.01765226,0.01114685,0.005714327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007158122,0.000255503,0.008733798,0.0005727999,0.0002088603,0.0002676165,0.002423203,0.01097284,0.001750641,0.5485123,0.1335616,0.292025],"study_design_scores_gemma":[0.0001117737,0.0003025452,0.002180707,0.0005913328,0.0000263452,0.0003602612,0.001394799,0.02682037,0.00133234,0.8567326,0.1100388,0.000108281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.04116412,0.02232653,0.2943934,0.5671064,0.005580738,0.0003244278,0.0007002825,0.002661311,0.0657428],"genre_scores_gemma":[0.6179945,0.006435226,0.2665245,0.08378796,0.007614209,0.0009701868,0.0007060676,0.001553554,0.01441387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0682693,"threshold_uncertainty_score":0.3610469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02752330254121815,"score_gpt":0.303763590257136,"score_spread":0.2762402877159179,"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."}}