{"id":"W4407361541","doi":"10.1109/tse.2025.3540549","title":"Search-Based DNN Testing and Retraining With GAN-Enhanced Simulations","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; European Space Agency; Science Foundation Ireland; Université du Luxembourg","keywords":"Computer science; Retraining; Artificial intelligence; Machine learning; Distributed computing; Computer architecture; Computer engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001100815,0.0001432864,0.0001253752,0.0003226898,0.0002372437,0.0001143194,0.0001941017,0.00005593456,0.000002807885],"category_scores_gemma":[0.00006297541,0.0001455286,0.00002572402,0.0008841905,0.000024927,0.0001840853,0.000002321367,0.0002431583,0.000001070933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005218506,"about_ca_system_score_gemma":0.00008544981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007601075,"about_ca_topic_score_gemma":0.000001580853,"domain_scores_codex":[0.9991913,0.00001947453,0.0001522435,0.0002905458,0.0001394573,0.0002069947],"domain_scores_gemma":[0.9988992,0.0006480083,0.00002451603,0.0002659894,0.000103759,0.00005849365],"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":[0.000003297739,0.00001672666,0.00004552235,0.00002418537,0.00001253895,0.000001784213,0.00009104101,0.9845937,0.0005247397,0.00005695369,0.000006036983,0.01462342],"study_design_scores_gemma":[0.0002363302,0.00006291848,0.0002128882,0.0002256002,0.000007075709,0.000002391725,0.000003921783,0.9511058,0.04795453,0.00001984835,0.00002225549,0.0001463834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006136669,0.00001787559,0.9917147,0.00006229807,0.0001123397,0.0001273472,0.000002856227,0.00172306,0.0001028164],"genre_scores_gemma":[0.5617683,0.000001033614,0.4381214,0.0000547877,0.000005106472,0.000008795743,3.545949e-7,0.000007974872,0.00003230191],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5556316,"threshold_uncertainty_score":0.5934483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01589608177396644,"score_gpt":0.2417518429268934,"score_spread":0.225855761152927,"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."}}