{"id":"W3149550336","doi":"10.1109/raise.2012.6227969","title":"Predicting mutation score using source code and test suite metrics","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Test suite; Computer science; Mutation; Mutation testing; Source code; Suite; Code coverage; Test case; Process (computing); Code (set theory); Reliability engineering; Programming language; Machine learning; Software; Set (abstract data type); Engineering; Biology; Genetics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0005019198,0.00008178357,0.00007858076,0.0001462501,0.0001447276,0.0001334126,0.0001802028,0.00004166175,0.000001425605],"category_scores_gemma":[0.001919914,0.00007318757,0.00001505971,0.0004796861,0.00002486241,0.0005183896,0.000178711,0.00007695411,0.000002759086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002736977,"about_ca_system_score_gemma":0.00001683042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001535111,"about_ca_topic_score_gemma":0.000002201766,"domain_scores_codex":[0.9992926,0.00002328769,0.0001259138,0.0001659758,0.000162544,0.0002296624],"domain_scores_gemma":[0.998486,0.001086704,0.00006862651,0.0002103864,0.00005848642,0.00008973206],"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":[2.429129e-7,0.00002005761,0.9705632,0.000009497922,0.000002096083,0.000001288878,0.0004707015,0.00002008275,0.0001409213,0.0005031577,0.0003391776,0.02792956],"study_design_scores_gemma":[0.0001386402,0.00006953335,0.06651471,0.00006506871,0.00001399254,0.0002712967,0.00002031128,0.9262053,0.003202592,0.002999024,0.0002531169,0.0002463777],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2941674,0.0001434084,0.7005764,0.00003648211,0.00007160262,0.00005304944,5.053367e-7,0.004755454,0.0001957392],"genre_scores_gemma":[0.6381158,0.000001270951,0.3616805,0.0001061229,0.00004797394,0.000001608979,4.528098e-7,0.000005546462,0.00004068632],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9261853,"threshold_uncertainty_score":0.2984503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05832407227421543,"score_gpt":0.2908110474789894,"score_spread":0.232486975204774,"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."}}