{"id":"W2743912071","doi":"10.1109/qrs.2017.55","title":"Automated Performance Deviation Detection across Software Versions Releases","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Granularity; Computer science; Software; Outlier; Standard deviation; Data mining; Interval (graph theory); Anomaly detection; TRACE (psycholinguistics); Confidence interval; Statistics; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003283437,0.0009510163,0.0008730827,0.004975216,0.0004642292,0.001754002,0.00107659,0.0006762449,0.00074651],"category_scores_gemma":[0.02996687,0.0003370198,0.0005057173,0.003096226,0.0004371796,0.001554951,0.001353786,0.001539394,0.0005492289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005423162,"about_ca_system_score_gemma":0.0007607413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003109783,"about_ca_topic_score_gemma":0.002664598,"domain_scores_codex":[0.9945629,0.0006297909,0.0004068338,0.001505804,0.002511266,0.0003834921],"domain_scores_gemma":[0.9738061,0.01061571,0.004705188,0.004458866,0.005808332,0.0006058409],"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":[0.0008787141,0.000485941,0.3650264,0.0003693889,0.0003085267,0.0007537459,0.001675486,0.05191172,0.05731919,0.002257414,0.004607741,0.5144057],"study_design_scores_gemma":[0.00004247842,0.0006677413,0.3159685,0.00005948047,0.0001086391,0.0009469584,0.0007890206,0.608393,0.06353823,0.004441815,0.004896082,0.0001480285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7636004,0.0003269303,0.2197934,0.0001781761,0.00005659166,0.0001098546,0.001701445,0.01254675,0.001686473],"genre_scores_gemma":[0.9622203,0.00005231719,0.03531081,0.00002161363,0.00002048939,0.00005095193,0.001654835,0.0003020874,0.0003665577],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004975216,"threshold_uncertainty_score":0.01736468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02154460755476916,"score_gpt":0.3000235910852413,"score_spread":0.2784789835304721,"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."}}