{"id":"W2125727889","doi":"10.1145/1368088.1368136","title":"Sufficient mutation operators for measuring test effectiveness","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":181,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mutant; Mutation testing; Test suite; Mutation; Measure (data warehouse); Computer science; Process (computing); Mathematics; Test case; Data mining; Genetics; Biology; Machine learning; Programming language; Gene","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":[0.01333238,0.002005143,0.001997803,0.007645034,0.0006736141,0.001492531,0.001863577,0.002903197,0.002793981],"category_scores_gemma":[0.08885669,0.0005421343,0.001333758,0.00283067,0.002223791,0.004002893,0.001332631,0.001388716,0.0009614908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001020524,"about_ca_system_score_gemma":0.001190352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006913241,"about_ca_topic_score_gemma":0.0006543014,"domain_scores_codex":[0.9551332,0.01348586,0.004839275,0.003390349,0.0217487,0.00140261],"domain_scores_gemma":[0.8653868,0.1007373,0.012469,0.009414095,0.009944702,0.002048032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00383034,0.001776652,0.1310738,0.002635005,0.001027775,0.001794962,0.0008616951,0.1995937,0.1944632,0.1229153,0.007316164,0.3327115],"study_design_scores_gemma":[0.0004508228,0.002797318,0.06105242,0.0005388951,0.0005194231,0.005045681,0.0003257138,0.6557104,0.1463473,0.1159014,0.01100059,0.0003101102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3793491,0.003615242,0.6006094,0.0004897168,0.0001455988,0.0006364717,0.002781363,0.003531559,0.008841516],"genre_scores_gemma":[0.8574812,0.0005051683,0.137912,0.0001937135,0.0001547128,0.0007030097,0.002073559,0.0004415056,0.0005349718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01333238,"threshold_uncertainty_score":0.0705092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04459589575011752,"score_gpt":0.266663017612815,"score_spread":0.2220671218626974,"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."}}