{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004604839,0.0003473124,0.0002727903,0.000304573,0.0001637962,0.0005566832,0.0005143632,0.0001279997,0.000005486373],"category_scores_gemma":[0.003716754,0.0003007473,0.00007247796,0.001788867,0.00004376517,0.0003601332,0.0001730268,0.0005093096,0.00001733593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002715062,"about_ca_system_score_gemma":0.000249433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006604102,"about_ca_topic_score_gemma":0.000002250365,"domain_scores_codex":[0.9979359,0.00005161928,0.0002743934,0.0006991413,0.0004784339,0.0005604955],"domain_scores_gemma":[0.9945896,0.004532092,0.00004253917,0.0004458142,0.0001737889,0.0002162083],"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":[0.00000283869,0.00003612791,0.07568794,0.0002374426,0.00002318834,0.000168457,0.0002103952,0.9183418,0.00008690227,0.0000359758,0.001760019,0.003408891],"study_design_scores_gemma":[0.0001664005,0.0002622106,0.004887213,0.0009815374,0.00001567629,0.00006682674,7.702866e-7,0.9912559,0.001301844,0.0001311418,0.0004622811,0.000468148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007342312,0.0001242526,0.9638934,0.0008975656,0.0001564055,0.0002434479,0.000008736138,0.0273138,0.0000201479],"genre_scores_gemma":[0.5022308,4.285669e-7,0.4973808,0.0001912418,0.00008827004,0.00004304827,0.000007521147,0.00004749534,0.00001047588],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4948884,"threshold_uncertainty_score":0.9999444,"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."}}