{"id":"W4284682233","doi":"10.1145/3510003.3510188","title":"Efficient online testing for DNN-enabled systems using surrogate-assisted and many-objective optimization","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 44th International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation of Korea; Fonds National de la Recherche Luxembourg; National Research Foundation; European Commission","keywords":"Computer science; Reliability (semiconductor); Fidelity; High fidelity; Reliability engineering; Software; Test strategy; Artificial neural network; Embedded system; Real-time computing; Distributed computing; Machine learning; Engineering; Operating system","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":[0.0004312145,0.0001689628,0.0001847031,0.0002249241,0.0002518678,0.0001701931,0.0008011797,0.00003698981,0.000002050008],"category_scores_gemma":[0.002048876,0.0001535914,0.00005204646,0.0004007235,0.0000251237,0.0001275272,0.0005465847,0.0002040514,8.42275e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002288497,"about_ca_system_score_gemma":0.00006788645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004118583,"about_ca_topic_score_gemma":1.010173e-7,"domain_scores_codex":[0.9987303,0.000009443706,0.0002925652,0.0003439778,0.0004239058,0.0001998185],"domain_scores_gemma":[0.998452,0.0003414527,0.0003002692,0.000124247,0.000738138,0.00004387177],"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":[0.00002334594,0.00008978755,0.005010437,0.0001281052,0.00004405057,8.265491e-7,0.0003042013,0.9667529,0.002098253,0.02445785,0.00008482401,0.00100541],"study_design_scores_gemma":[0.0002399419,0.0001080859,0.00126514,0.0002953003,0.00001090512,0.00005146291,0.00005496705,0.9969341,0.0004343108,0.0004274092,0.00001743306,0.0001610032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2306265,0.00003793511,0.7660061,0.0001332065,0.0008051607,0.0004877729,0.00004719173,0.001779753,0.00007641334],"genre_scores_gemma":[0.6722386,6.59212e-7,0.3275905,0.00002238413,0.0000342654,0.00006988574,0.000002941674,0.00001586846,0.00002491005],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4416121,"threshold_uncertainty_score":0.6263278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04979620041711109,"score_gpt":0.266732807629432,"score_spread":0.2169366072123209,"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."}}