{"id":"W4403223004","doi":"10.1145/3689793","title":"Making Sense of Multi-threaded Application Performance at Scale with NonSequitur","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sense (electronics); Computer science; Scale (ratio); Engineering; Electrical engineering; Geography; Cartography","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":[0.0004849749,0.0001526545,0.0001921679,0.00009239349,0.0001193017,0.00008313039,0.00117896,0.00006839754,0.000001118244],"category_scores_gemma":[0.0001096377,0.00008703841,0.00008232034,0.0005964913,0.000141575,0.0003100823,0.0006528758,0.0001480506,0.000008776223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006330245,"about_ca_system_score_gemma":0.000030894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001653589,"about_ca_topic_score_gemma":0.000004126721,"domain_scores_codex":[0.9987639,0.000006931414,0.0002605874,0.0003641819,0.0003709387,0.0002334576],"domain_scores_gemma":[0.9989198,0.00006835275,0.0002000774,0.0006177467,0.0001637503,0.0000302742],"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":[0.0001675763,0.0003387669,0.1808144,0.007016066,0.0001356335,0.000004429555,0.01609237,0.0001145087,0.07199163,0.002521126,0.0002998568,0.7205037],"study_design_scores_gemma":[0.0008988614,0.0009102633,0.04810451,0.004782625,0.0001094891,0.0003214102,0.001613865,0.03094661,0.907791,0.0003657322,0.003457908,0.0006976943],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966583,0.0004336056,0.001249869,0.0005019298,0.0001058243,0.0005221943,0.000001765517,0.0002976972,0.0002287998],"genre_scores_gemma":[0.955081,0.00001092942,0.04458909,0.00002907901,0.00003878532,0.00007526496,5.976118e-7,0.00001484446,0.0001604117],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8357994,"threshold_uncertainty_score":0.3549323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02078093307109422,"score_gpt":0.2860024398985674,"score_spread":0.2652215068274731,"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."}}