{"id":"W4409262526","doi":"10.1109/wacv61041.2025.00614","title":"Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance","year":2025,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Robustness (evolution); Computer science; Artificial neural network; Artificial intelligence; Language change","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":[0.004283623,0.0009416901,0.0005754113,0.001033262,0.0003563742,0.001389445,0.0007497215,0.001074785,0.001814833],"category_scores_gemma":[0.03371372,0.0002394799,0.0004754025,0.0004242286,0.00127649,0.001780169,0.001793998,0.0008871014,0.0005526256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006251575,"about_ca_system_score_gemma":0.000399044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002011796,"about_ca_topic_score_gemma":0.002178474,"domain_scores_codex":[0.9966557,0.001125644,0.0002545241,0.0008020478,0.0009117509,0.0002502922],"domain_scores_gemma":[0.9874825,0.00678239,0.001849711,0.001918835,0.001553027,0.0004134803],"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":[0.002945055,0.0004616397,0.0822285,0.001575234,0.0009164235,0.0006452938,0.001766603,0.3128315,0.1262863,0.005663035,0.006089639,0.4585908],"study_design_scores_gemma":[0.00007548439,0.002522638,0.1037411,0.0002994034,0.0003388572,0.001376943,0.0009437382,0.7530409,0.1145081,0.01653432,0.006382465,0.0002360608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7577113,0.00186275,0.2290383,0.0004446547,0.0003089011,0.0001943527,0.0006421643,0.001958238,0.007839289],"genre_scores_gemma":[0.9762524,0.000193589,0.02216544,0.00009210729,0.00003450086,0.00003496452,0.0003836375,0.0001339362,0.0007094124],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004283623,"threshold_uncertainty_score":0.02265424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01966534667968344,"score_gpt":0.3176014962214103,"score_spread":0.2979361495417268,"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."}}