{"id":"W4384345647","doi":"10.1109/icse48619.2023.00152","title":"Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation","year":2023,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; Japan Society for the Promotion of Science; Department of Forestry and Natural Resources, Purdue University; Japan Science and Technology Corporation; Japan Society for the Promotion of Science London; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Labeled data; Artificial neural network; Machine learning; Deep neural networks; Deep learning; Test data; Key (lock); De facto; Set (abstract data type); Data mining; Transformation (genetics); Data set; Test set","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006272027,0.0001450137,0.0001806648,0.0001517448,0.0002108321,0.0001066819,0.001159566,0.00006414857,0.0000145131],"category_scores_gemma":[0.004187932,0.0001332447,0.00004772764,0.001680853,0.00005405335,0.0003197658,0.001021937,0.00024376,0.00002653848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003017979,"about_ca_system_score_gemma":0.00002351817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009249687,"about_ca_topic_score_gemma":0.000007349303,"domain_scores_codex":[0.9985077,0.00008562809,0.0003633163,0.0003372239,0.0003525818,0.0003535682],"domain_scores_gemma":[0.9972303,0.001643782,0.0002266351,0.0006884321,0.0001464824,0.00006440059],"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":[0.000002367966,0.00001102947,0.0007791494,0.00001199918,0.000005148151,0.000006455742,0.0002787929,0.8790135,0.00008213365,0.003899454,0.00004413908,0.1158659],"study_design_scores_gemma":[0.0002567319,0.00003805975,0.001592989,0.00001646235,0.000006366637,0.000006723344,0.00002969105,0.9961119,0.00009686502,0.001696944,0.000008711939,0.0001385391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02269274,0.0000245122,0.9747282,0.0004681747,0.0005731426,0.0001374495,2.718838e-7,0.000766637,0.0006088499],"genre_scores_gemma":[0.7204277,4.631246e-7,0.2793915,0.00007234626,0.00006494969,0.000005281242,0.000003467151,0.00001097776,0.0000233821],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.697735,"threshold_uncertainty_score":0.5433562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02082330005433738,"score_gpt":0.2748311056085461,"score_spread":0.2540078055542088,"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."}}