{"id":"W3165074812","doi":"10.1145/3460946.3464318","title":"PerfLens: a data-driven performance bug detection and fix platform","year":2021,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Codebase; Computer science; Leverage (statistics); Source code; Open source; Software; Performance improvement; Software bug; Code (set theory); Database; Software engineering; Operating system; Engineering; Artificial intelligence; Programming language","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":[0.0002852362,0.0001148055,0.000146718,0.00004340171,0.0002066381,0.0001462284,0.0005276339,0.00007341164,0.0000313763],"category_scores_gemma":[0.00004662417,0.00008943734,0.00002495329,0.0002869712,0.00003955837,0.001593081,0.0007279386,0.0001270185,0.00008970608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003214942,"about_ca_system_score_gemma":0.00009178418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003249193,"about_ca_topic_score_gemma":0.00006839513,"domain_scores_codex":[0.9988207,0.00002177022,0.0002067345,0.0005186698,0.0002113519,0.0002208123],"domain_scores_gemma":[0.9985226,0.00005671279,0.00004538624,0.001194996,0.000106254,0.00007403622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000246012,0.0001516767,0.09334087,0.0005107339,0.00007243849,0.00003952108,0.001708623,0.0002443806,0.002840281,0.001028605,0.00163024,0.898408],"study_design_scores_gemma":[0.0006001415,0.0001515452,0.08761328,0.00006961882,0.00001296489,0.0004471999,0.0001590751,0.8750238,0.01322053,0.0002039098,0.02210973,0.0003881682],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.90694,0.0002553448,0.08958036,0.0002821058,0.0005537209,0.000119131,0.000003143922,0.0002888717,0.001977344],"genre_scores_gemma":[0.9887434,0.0002151366,0.01025183,0.0002045652,0.0000836266,0.000008494228,0.000007164685,0.000005309931,0.0004805149],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8980199,"threshold_uncertainty_score":0.3647149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03282886291339494,"score_gpt":0.2485235991373104,"score_spread":0.2156947362239154,"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."}}