{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002368916,0.001816788,0.001566259,0.0007041285,0.0004050014,0.001024822,0.001814977,0.001660745,0.0034911],"category_scores_gemma":[0.009252509,0.0008935453,0.0007874873,0.0003856623,0.001253493,0.0014002,0.001580418,0.002203793,0.0004100159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001550891,"about_ca_system_score_gemma":0.00208294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007239142,"about_ca_topic_score_gemma":0.009303014,"domain_scores_codex":[0.998786,0.0005264807,0.0000636913,0.0001725336,0.0002533577,0.0001978837],"domain_scores_gemma":[0.9929404,0.005540471,0.0004069603,0.0002764438,0.0005895043,0.0002462435],"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":[0.00009335129,0.00004541429,0.0005710026,0.00007457626,0.00002481447,0.00005376924,0.00001494021,0.983582,0.0005741476,0.00146863,0.0003930918,0.01310433],"study_design_scores_gemma":[0.000005755069,0.00001557319,0.00003466857,0.000004571953,0.000002063643,0.000004526283,0.000002764005,0.9986965,0.0001781731,0.001004612,0.00004948891,0.000001402174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1092925,0.001118562,0.8798147,0.0008583917,0.0001177667,0.0001725513,0.0002409004,0.002692421,0.005692321],"genre_scores_gemma":[0.8764865,0.0001507102,0.1202875,0.0002680805,0.00002506075,0.0001995299,0.0004287919,0.0002642374,0.001889471],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007239142,"threshold_uncertainty_score":0.01439399,"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."}}