{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003897777,0.00007824453,0.00008648329,0.00007145019,0.0002127296,0.00004785206,0.0002816533,0.00002801187,9.072599e-7],"category_scores_gemma":[0.0008400108,0.00006674838,0.00003643898,0.0002194003,0.00002215729,0.0001623255,0.0000593292,0.0000374531,0.000008091025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004183252,"about_ca_system_score_gemma":0.00005000261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003773022,"about_ca_topic_score_gemma":9.309523e-7,"domain_scores_codex":[0.9993442,0.00002928458,0.0001009487,0.0002368239,0.0001353491,0.0001533943],"domain_scores_gemma":[0.998567,0.0009861529,0.00002654075,0.0002384273,0.0001408167,0.0000410248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007287495,0.002582564,0.5893288,0.0006406818,0.00009822672,0.0003648295,0.009866153,0.008115077,0.0199405,0.08927833,0.04993952,0.2297725],"study_design_scores_gemma":[0.001327283,0.001204617,0.15019,0.0002148883,0.0000114545,0.0005266875,0.00001316913,0.4772036,0.3468841,0.02074648,0.0007483973,0.000929252],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1494028,0.0000189024,0.8436256,0.00004291695,0.0001072248,0.0002138001,4.773085e-7,0.006269137,0.0003191885],"genre_scores_gemma":[0.7854305,6.428422e-7,0.2143798,0.0000666054,0.00001809448,0.00006721666,7.210958e-7,0.000005602853,0.00003084149],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6360278,"threshold_uncertainty_score":0.272192,"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."}}