{"id":"W4404406203","doi":"10.1007/s10664-024-10564-3","title":"Can search-based testing with pareto optimization effectively cover failure-revealing test inputs?","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; HORIZON EUROPE Reforming and enhancing the European Research and Innovation system; Technische Universität München; European Commission","keywords":"Cover (algebra); Pareto principle; Reliability engineering; Computer science; Engineering; Mathematical optimization; Mathematics; Mechanical engineering","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":[0.003103406,0.0009368361,0.0008325371,0.001068147,0.0004025681,0.0008630469,0.001134423,0.0009469823,0.001632545],"category_scores_gemma":[0.0141244,0.0003152388,0.0008370354,0.0006115877,0.001191332,0.001360031,0.0009518348,0.0009317509,0.0002341742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001130209,"about_ca_system_score_gemma":0.00163212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005190806,"about_ca_topic_score_gemma":0.003724466,"domain_scores_codex":[0.9983284,0.000733009,0.00007184039,0.0001680804,0.0004312603,0.000267376],"domain_scores_gemma":[0.9927468,0.005231422,0.0004699796,0.0006399328,0.0006762416,0.0002357387],"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":[0.0001051047,0.000102289,0.002934349,0.00004968298,0.00004001261,0.00006973785,0.00004095828,0.9617073,0.002202952,0.004160943,0.0003804757,0.02820613],"study_design_scores_gemma":[0.0000139022,0.00008284969,0.0004274264,0.00001244549,0.00000946207,0.00001685999,0.00002484265,0.9940865,0.001258876,0.003874294,0.0001889603,0.000003498697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4242346,0.0005270579,0.565913,0.0008712879,0.00005649536,0.000153588,0.0001144389,0.0007971416,0.007332402],"genre_scores_gemma":[0.9578573,0.00006134636,0.0413006,0.0001070322,0.000008509154,0.00006598467,0.00007140204,0.00004893693,0.0004787323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005190806,"threshold_uncertainty_score":0.01641256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02105501579744261,"score_gpt":0.2553548562089946,"score_spread":0.2342998404115519,"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."}}