{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0154156,0.0009352757,0.0009920743,0.00529376,0.001617654,0.005271316,0.002851665,0.001671046,0.002046211],"category_scores_gemma":[0.08073096,0.0009141829,0.0008831506,0.00427132,0.002582885,0.009963146,0.00571122,0.002714842,0.0002888413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001920054,"about_ca_system_score_gemma":0.007533018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004378379,"about_ca_topic_score_gemma":0.007469158,"domain_scores_codex":[0.990414,0.005906951,0.0005483281,0.0007267053,0.002068714,0.0003353023],"domain_scores_gemma":[0.9130138,0.05733207,0.005437398,0.0182446,0.005077336,0.0008947616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000206039,0.002020955,0.07503795,0.0009524527,0.0005098137,0.0002286083,0.004950956,0.1415518,0.01062163,0.2497507,0.001750245,0.5124189],"study_design_scores_gemma":[0.00007670966,0.0006732575,0.04537623,0.0006658193,0.0005081163,0.000305566,0.002911848,0.5731329,0.01410242,0.3521633,0.00994521,0.0001385819],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07280909,0.0003333727,0.9195613,0.000893897,0.00002028202,0.0001922181,0.00009845919,0.0007193362,0.005372069],"genre_scores_gemma":[0.5956231,0.0005392254,0.401837,0.0001663094,0.00003842732,0.0001795426,0.0001096518,0.0001770965,0.001329585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0154156,"threshold_uncertainty_score":0.08152652,"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."}}