{"id":"W3178956269","doi":"10.1007/s10664-021-10004-6","title":"Evaluating the impact of falsely detected performance bug-inducing changes in JIT models","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; Polytechnique Montréal; Concordia University","funders":"","keywords":"Leverage (statistics); Software bug; Computer science; Software; Software quality; Empirical research; Software quality assurance; Quality (philosophy); Capability Maturity Model; Source code; Software engineering; Software development; Operating system; Artificial intelligence","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":[0.0009117905,0.0002564127,0.0003265537,0.0002487483,0.00007799259,0.00009887153,0.0008806887,0.0001183155,0.00001784961],"category_scores_gemma":[0.004146754,0.0002027383,0.000129324,0.001949553,0.00002427539,0.0003904878,0.0005087447,0.0005994975,0.000007512048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000310131,"about_ca_system_score_gemma":0.0002614035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006984235,"about_ca_topic_score_gemma":0.000008422672,"domain_scores_codex":[0.9977514,0.00008817369,0.0003547386,0.0004877521,0.0006455121,0.0006723888],"domain_scores_gemma":[0.9966437,0.002156308,0.00006390115,0.0007829524,0.0002174389,0.0001356491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004570619,0.00003329673,0.1013249,0.00007102894,0.00003069766,0.0000242837,0.0008176127,0.8833954,0.004515788,0.00001117356,0.00002250774,0.009748791],"study_design_scores_gemma":[0.0002065992,0.0001309483,0.3223307,0.0001343426,0.000002907706,0.00002997736,0.000006314343,0.6697695,0.007150152,0.00004603784,0.000007651085,0.0001849506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7388585,0.0004132125,0.2600238,0.0001063101,0.0001329596,0.0001326455,0.000002028489,0.0003251552,0.000005386173],"genre_scores_gemma":[0.9633771,0.0000223754,0.0363963,0.00001879628,0.00007352079,0.00004943877,0.000002479207,0.00003577323,0.00002424699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2245185,"threshold_uncertainty_score":0.8267428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09454756759896381,"score_gpt":0.3660511802990926,"score_spread":0.2715036127001288,"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."}}