{"id":"W4403576996","doi":"10.48550/arxiv.2410.11769","title":"Can Search-Based Testing with Pareto Optimization Effectively Cover Failure-Revealing Test Inputs?","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Cover (algebra); Pareto principle; Test (biology); Computer science; Pareto optimal; Reliability engineering; Mathematical optimization; Multi-objective optimization; Mathematics; Engineering; Geology; Paleontology","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":[0.0005132179,0.0004710643,0.000384929,0.0005154113,0.000252999,0.0004624887,0.001340079,0.0002830446,0.000004484414],"category_scores_gemma":[0.0006086908,0.0004785155,0.0001203129,0.001669738,0.0001618012,0.0001921009,0.001690061,0.001044034,0.0000279601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004811596,"about_ca_system_score_gemma":0.0008100448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007502814,"about_ca_topic_score_gemma":0.00004450138,"domain_scores_codex":[0.9974131,0.0001889176,0.0002152307,0.00148994,0.0002078049,0.0004850265],"domain_scores_gemma":[0.9965359,0.001464636,0.0002186757,0.00111257,0.0004683178,0.0001998947],"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":[0.00001122616,0.00005625591,0.01887899,0.0002700297,0.00004385815,0.0005153351,0.0001201286,0.9776068,0.00001738692,0.001555462,0.0005701423,0.0003543767],"study_design_scores_gemma":[0.0002781442,0.0002232711,0.000470583,0.001394291,0.00008364505,0.00001645322,0.000004544768,0.9798371,0.0004633123,0.01661982,0.00001475011,0.0005940555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03218967,0.0000261652,0.9557202,0.0003741272,0.0001599801,0.0004913905,0.00003053938,0.01041004,0.0005978445],"genre_scores_gemma":[0.8317044,0.000002691076,0.167891,0.0001472997,0.00006006395,0.000005005597,0.00002196093,0.00004816929,0.0001194572],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7995147,"threshold_uncertainty_score":0.9997666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05888171160340358,"score_gpt":0.1974152998554705,"score_spread":0.1385335882520669,"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."}}