{"id":"W2614734074","doi":"10.1109/icst.2017.17","title":"Perphecy: Performance Regression Test Selection Made Simple but Effective","year":2017,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Regression testing; Computer science; Commit; Generality; Regression; Simple (philosophy); Selection (genetic algorithm); Regression analysis; Machine learning; Software; Statistics; Software system; Mathematics; Operating system","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0004671273,0.0001750321,0.0001928526,0.00005816741,0.001311083,0.0003443581,0.001011735,0.0001154911,0.00003849194],"category_scores_gemma":[0.0002642299,0.0001169574,0.0000730762,0.0001185098,0.00008048288,0.00158445,0.0003427521,0.0001861469,0.0003244881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009885082,"about_ca_system_score_gemma":0.00006564138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001835622,"about_ca_topic_score_gemma":0.0000186507,"domain_scores_codex":[0.9986851,0.00004210048,0.0002008256,0.0004636309,0.0002827553,0.0003256548],"domain_scores_gemma":[0.9983196,0.0001468025,0.000178637,0.0011134,0.000147391,0.0000941219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000108074,0.00008031797,0.8261369,0.00009131803,0.000009772789,0.000002514364,0.000224494,0.00004697514,0.003078092,0.0002353925,0.001867247,0.1682162],"study_design_scores_gemma":[0.0004081627,0.000299882,0.869124,0.00007455633,0.000004900339,0.00004006291,0.00001572389,0.07888177,0.04767239,0.0003573521,0.002871573,0.0002496054],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.955003,0.0000244769,0.03530297,0.00038623,0.0006801775,0.0004079314,0.000001196118,0.0004389262,0.00775514],"genre_scores_gemma":[0.9940869,0.00002378712,0.003322257,0.00008022402,0.0001889323,0.00005607154,0.000001221177,0.000008735868,0.002231863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1679666,"threshold_uncertainty_score":0.9999891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009765202068299257,"score_gpt":0.2605345804974529,"score_spread":0.2507693784291536,"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."}}