{"id":"W2147386665","doi":"10.1109/tse.2012.70","title":"A large-scale empirical study of just-in-time quality assurance","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":699,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Polytechnique Montréal","funders":"","keywords":"Computer science; Software quality assurance; Quality assurance; Source lines of code; Quality (philosophy); Software quality; Code review; Scale (ratio); Software; Empirical research; Software quality analyst; Software bug; Data science; Software engineering; Software development; Operations management; Engineering","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"],"consensus_categories":[],"category_scores_codex":[0.001012411,0.0002524311,0.0003892574,0.0004684996,0.00006686229,0.0000421339,0.0007570104,0.0001184865,0.00003177331],"category_scores_gemma":[0.0002268539,0.0002722981,0.0001150616,0.0012466,0.00001543389,0.0005652808,0.00001343388,0.0005516079,0.00006862677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001618104,"about_ca_system_score_gemma":0.00004563351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002314978,"about_ca_topic_score_gemma":0.00001388559,"domain_scores_codex":[0.9975502,0.00009868422,0.00047877,0.0004006882,0.0007518968,0.0007197341],"domain_scores_gemma":[0.9973338,0.001505229,0.00005054292,0.0008143466,0.0000762674,0.0002198507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00005005165,0.006012518,0.3428673,0.0003028623,0.0001500655,0.00002677662,0.01719011,0.6293525,0.001325534,0.00002662956,0.0001577823,0.002537933],"study_design_scores_gemma":[0.003371616,0.0006152564,0.9062577,0.0002398083,0.00003534183,0.00003427537,0.0004306241,0.07069996,0.01653085,0.00000615331,0.0005715288,0.001206884],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4709621,0.00003521477,0.528027,0.000009744618,0.0003797666,0.000185237,0.000006736391,0.0003913671,0.000002827599],"genre_scores_gemma":[0.9703541,0.000003844004,0.02937187,0.00001717336,0.00004497297,0.00009999869,5.231033e-7,0.00003759837,0.00006989297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5633904,"threshold_uncertainty_score":0.9999729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03357803100855729,"score_gpt":0.3186450643686469,"score_spread":0.2850670333600896,"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."}}