{"id":"W4399294975","doi":"10.1016/j.jss.2024.112117","title":"Enhancing empirical software performance engineering research with kernel-level events: A comprehensive system tracing approach","year":2024,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brock University","funders":"","keywords":"Computer science; Tracing; Empirical research; Kernel (algebra); Software engineering; Programming language; Mathematics; Statistics","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":[0.002681844,0.0003232574,0.0007202753,0.0005706535,0.0003557511,0.0005405097,0.0006595121,0.0002032573,6.566852e-7],"category_scores_gemma":[0.0001383566,0.0002119197,0.0001487415,0.0009723422,0.00006964162,0.00141465,0.0001956598,0.0009933872,0.00001169498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003947754,"about_ca_system_score_gemma":0.0004273079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004040505,"about_ca_topic_score_gemma":0.000001269402,"domain_scores_codex":[0.9963509,0.0002244743,0.001011452,0.0005263578,0.001289761,0.0005970268],"domain_scores_gemma":[0.997273,0.00069619,0.0002550901,0.0004918813,0.0009907744,0.0002930561],"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":[0.0007124986,0.0009384957,0.4966346,0.1762126,0.003424564,0.003733222,0.07323955,0.1606934,0.001761962,0.003740791,0.005842302,0.073066],"study_design_scores_gemma":[0.00560758,0.005841544,0.1641323,0.09131829,0.0003613798,0.06735042,0.02104917,0.6220508,0.0014535,0.0001252523,0.01696777,0.003742025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.45655,0.008594525,0.5332276,0.00003726074,0.001037235,0.0002964091,0.000004892117,0.000235022,0.00001708826],"genre_scores_gemma":[0.962256,0.0001182853,0.0369373,0.00001115119,0.0005155088,0.00003143074,0.000001267846,0.00003826319,0.00009076267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5057061,"threshold_uncertainty_score":0.8641836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06103167280170042,"score_gpt":0.3003110414255424,"score_spread":0.239279368623842,"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."}}