{"id":"W4367692815","doi":"10.48550/arxiv.2305.00083","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":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Computer science; Benchmark (surveying); Replication (statistics); Taxonomy (biology); Generalization; Machine learning; Heuristic; Artificial intelligence; Domain (mathematical analysis); Reliability engineering; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007970613,0.0003329613,0.0003615243,0.0006474208,0.0004074481,0.0001717388,0.000600183,0.0002463115,4.369671e-7],"category_scores_gemma":[0.001269401,0.0003664868,0.00007795091,0.001020317,0.0001853111,0.0001551433,0.0007718733,0.0007601787,0.000005086961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002769146,"about_ca_system_score_gemma":0.0003495406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005349463,"about_ca_topic_score_gemma":0.00004520932,"domain_scores_codex":[0.9974561,0.0002867842,0.000231689,0.001582092,0.0001473258,0.0002959838],"domain_scores_gemma":[0.9953999,0.00238789,0.0002438992,0.001473638,0.0003360037,0.0001586983],"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":[0.0001191595,0.0001660813,0.006078694,0.00009336661,0.0000740773,0.000136985,0.0001107589,0.9787765,0.00001256842,0.006838238,0.001243272,0.006350329],"study_design_scores_gemma":[0.0007828886,0.0003219203,0.0007253092,0.0005531596,0.00004664778,0.00000205908,0.00001793098,0.9580811,0.00008472963,0.03900115,0.00004560145,0.0003374459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1441168,0.00003170883,0.8403856,0.001089988,0.0003547248,0.001243161,0.00003335912,0.01194066,0.0008039734],"genre_scores_gemma":[0.9717351,0.0000162142,0.02781416,0.000189641,0.00005678877,0.00001978246,0.00001591503,0.00002599489,0.0001263506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8276184,"threshold_uncertainty_score":0.9998787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6868043205396952,"score_gpt":0.3359967428355055,"score_spread":0.3508075777041897,"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."}}