{"id":"W7133017312","doi":"","title":"Analyzing System Performance and Automating Performance Diagnosis","year":2025,"lang":"","type":"dissertation","venue":"TSpace","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Root cause; Debugging; Software; Software performance testing; Software system; Root (linguistics); Kernel (algebra); Linux kernel; Root cause analysis","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.002020395,0.001206602,0.001570765,0.0007931388,0.002065518,0.0008690384,0.001643255,0.0008892959,0.00003974987],"category_scores_gemma":[0.0002182645,0.001152553,0.0003175122,0.002188097,0.0001478135,0.001547146,0.0006152081,0.001167674,0.0001694097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006334042,"about_ca_system_score_gemma":0.000884478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004603859,"about_ca_topic_score_gemma":0.00003838305,"domain_scores_codex":[0.9936917,0.0003107661,0.001683444,0.002053561,0.000964673,0.001295787],"domain_scores_gemma":[0.9951755,0.0006084393,0.001260234,0.001885957,0.000716618,0.0003532024],"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":[0.0001049949,0.0001480939,0.4703219,0.05658562,0.0003526461,0.00001987211,0.0312935,0.002145451,0.00006904249,0.0004429818,0.0005240887,0.4379918],"study_design_scores_gemma":[0.0007984308,0.0003835831,0.1733643,0.02005299,0.0003166977,0.00006321588,0.006467897,0.7927115,0.003074613,0.000003432003,0.001248255,0.001515068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9766424,0.004026341,0.00396972,0.0001719397,0.004612414,0.0013128,0.000006476642,0.0008945789,0.008363319],"genre_scores_gemma":[0.9838353,0.004226204,0.003394983,0.00004146049,0.0003128304,0.0004999331,0.00005421879,0.00005867681,0.007576439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7905661,"threshold_uncertainty_score":0.9992337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01390179348402464,"score_gpt":0.2868689710556617,"score_spread":0.272967177571637,"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."}}