{"id":"W4406957873","doi":"10.1145/3715693","title":"Assessing the Robustness of Test Selection Methods for Deep Neural Networks","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Artificial neural network; Machine learning; Robustness testing; Biology","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":[0.001819004,0.0001556036,0.0002735436,0.0002025935,0.0002827023,0.00006163017,0.0004845265,0.0001431656,0.000002000859],"category_scores_gemma":[0.004381888,0.0001299278,0.00008879728,0.0006005077,0.00005261452,0.0002232865,0.00003088522,0.0004405169,4.551709e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002989438,"about_ca_system_score_gemma":0.0000274429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009784827,"about_ca_topic_score_gemma":0.000002233125,"domain_scores_codex":[0.998664,0.0004839945,0.0002473605,0.0003067636,0.00005688325,0.0002410342],"domain_scores_gemma":[0.9812344,0.0181815,0.00007910877,0.0003797215,0.00009191904,0.00003332253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004006931,0.000009931523,0.00008260869,0.00002663092,0.00002618341,1.103506e-7,0.00005773063,0.6243794,0.0001547834,0.0006390249,0.000001292894,0.3746183],"study_design_scores_gemma":[0.0002353577,0.00006536816,0.001009058,0.00002251984,0.00005782117,0.00001949113,0.00003740157,0.9967154,0.0009860122,0.0004329022,0.0003108864,0.0001077385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006319021,0.0002189114,0.996873,0.0003850269,0.001468243,0.0001794492,5.400059e-7,0.0002402578,0.000002722546],"genre_scores_gemma":[0.07935718,0.0000125248,0.9204059,0.00007018936,0.00005086027,0.00006003127,7.629041e-7,0.00001345455,0.00002908139],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3745106,"threshold_uncertainty_score":0.5298303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05595642973612091,"score_gpt":0.3873494532374797,"score_spread":0.3313930235013587,"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."}}