{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007423064,0.0000928671,0.0001449743,0.0005623497,0.00005615777,0.0003163908,0.0002195962,0.00004884085,0.0001897054],"category_scores_gemma":[0.00008141006,0.00007279732,0.0001194427,0.000401247,0.00001157616,0.001155537,0.00005578883,0.0003142102,0.00005596391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006379707,"about_ca_system_score_gemma":0.00005244437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001860917,"about_ca_topic_score_gemma":0.0000483923,"domain_scores_codex":[0.9988756,0.0000817391,0.0004537354,0.0001644993,0.0003016136,0.0001228339],"domain_scores_gemma":[0.9994452,0.0001115001,0.0001317406,0.0001051993,0.0001474179,0.00005896499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001807501,0.00007407084,0.0004673584,0.00003748321,0.00001088546,0.0001171657,0.0008858234,0.00002778587,0.001699363,0.0002298195,0.004169244,0.9922629],"study_design_scores_gemma":[0.003507312,0.003918845,0.1562662,0.006853193,0.00009024687,0.002992857,0.0001524231,0.38216,0.00349149,0.3452159,0.09412935,0.001222197],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6365404,0.002431722,0.3450256,0.003216669,0.009057199,0.0001845151,0.000006304753,0.0001723053,0.003365281],"genre_scores_gemma":[0.9911332,0.0001646572,0.007992196,0.0001099567,0.0005345066,0.000001481355,0.0000029544,0.000007519574,0.000053594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9910407,"threshold_uncertainty_score":0.3050964,"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."}}