{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04377779,0.0010552,0.001627108,0.003994398,0.002563825,0.00935581,0.006916993,0.005920365,0.004096331],"category_scores_gemma":[0.1047809,0.0008424991,0.001252362,0.004657225,0.02187498,0.03124348,0.005590797,0.008770133,0.000783935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006742122,"about_ca_system_score_gemma":0.006868206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01259716,"about_ca_topic_score_gemma":0.005817855,"domain_scores_codex":[0.9604964,0.02602384,0.001882614,0.001775992,0.008792819,0.001028293],"domain_scores_gemma":[0.8154593,0.1357372,0.003502236,0.02788325,0.01612595,0.001292106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001214134,0.0003482255,0.00144864,0.0003742448,0.00001798464,0.0002579688,0.01016277,0.00733326,0.0009095062,0.8980718,0.004769397,0.07618479],"study_design_scores_gemma":[0.0001299096,0.0008792158,0.001553674,0.00179978,0.00004461619,0.001007967,0.01832526,0.05870734,0.005728743,0.7933796,0.1182776,0.0001662776],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06672654,0.02928812,0.7137682,0.08880324,0.0008888606,0.0009240317,0.000185841,0.0006392476,0.09877587],"genre_scores_gemma":[0.7262337,0.01798897,0.2378243,0.005323619,0.0004556234,0.0009405598,0.0001757751,0.0004588445,0.01059864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04377779,"threshold_uncertainty_score":0.2315218,"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."}}