{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004554421,0.001033009,0.0004769546,0.002975137,0.000641384,0.002712189,0.001624472,0.0007467453,0.002056496],"category_scores_gemma":[0.04990743,0.0006156443,0.000381025,0.001250501,0.0009982684,0.005641042,0.003208636,0.001162305,0.0005662348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006095931,"about_ca_system_score_gemma":0.0006278384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002837626,"about_ca_topic_score_gemma":0.003948294,"domain_scores_codex":[0.996686,0.001042549,0.0001758836,0.0007665698,0.001153849,0.000175217],"domain_scores_gemma":[0.9706144,0.016457,0.003376653,0.0049869,0.003523014,0.001042004],"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":[0.002182259,0.0006620502,0.1686568,0.0008810032,0.0004238159,0.0009405023,0.02083962,0.02566524,0.05863059,0.01017343,0.0150454,0.6958992],"study_design_scores_gemma":[0.0002145868,0.001720236,0.2398158,0.0003084959,0.0002582213,0.001711658,0.01526983,0.5529062,0.06407982,0.076393,0.04683837,0.0004839674],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7388953,0.0006333527,0.2339675,0.001511036,0.0001563084,0.000258077,0.001225112,0.01642269,0.006930661],"genre_scores_gemma":[0.9166662,0.0001654415,0.07968332,0.000151101,0.00004561777,0.0001614637,0.0008950349,0.001054506,0.001177345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004554421,"threshold_uncertainty_score":0.02408636,"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."}}