{"id":"W4381853525","doi":"10.1016/j.infsof.2023.107286","title":"Reflections on Surrogate-Assisted Search-Based Testing: A Taxonomy and Two Replication Studies based on Industrial ADAS and Simulink Models","year":2023,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; University of Ottawa","funders":"Horizon 2020; HORIZON EUROPE Framework Programme; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme","keywords":"Computer science; Benchmark (surveying); Replication (statistics); Machine learning; Heuristic; Taxonomy (biology); Generalization; Artificial intelligence; Reliability engineering; Search-based software engineering; Software; Engineering; Software system; Programming language","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":[0.0006200064,0.000172618,0.0002067304,0.001108583,0.0003996286,0.0001435845,0.0002141523,0.0001998711,3.583112e-7],"category_scores_gemma":[0.00336275,0.0001603693,0.00001896048,0.001356594,0.0001913557,0.000458762,0.0001746862,0.0003166319,0.000007316461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006195829,"about_ca_system_score_gemma":0.0001101441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004257406,"about_ca_topic_score_gemma":0.000006769914,"domain_scores_codex":[0.9988533,0.00005272152,0.0003298686,0.0003417543,0.0001884005,0.000233903],"domain_scores_gemma":[0.9978443,0.001107383,0.0001561461,0.0005676873,0.0002549348,0.00006955203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005075825,0.00005048915,0.009915852,0.00007198673,0.0000218324,0.000007096685,0.0004020452,0.008270482,0.00001561965,0.008886407,0.002944926,0.9693625],"study_design_scores_gemma":[0.001604642,0.0008899241,0.002036838,0.0002583473,0.00001217099,0.00003025853,0.0001065334,0.9591013,0.0004304593,0.03297262,0.002230058,0.0003268432],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1416405,0.000086406,0.7960034,0.01168858,0.0002119437,0.001368427,0.00002581758,0.04845904,0.0005159268],"genre_scores_gemma":[0.8856675,0.00001559352,0.1131972,0.0008464471,0.00001367818,0.0002221301,0.0000202027,0.00000839867,0.000008863295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9690357,"threshold_uncertainty_score":0.653967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2884403668754432,"score_gpt":0.3828625042578708,"score_spread":0.09442213738242755,"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."}}