{"id":"W4233479913","doi":"10.1109/msr.2012.6224280","title":"Explaining software defects using topic models","year":2012,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Software quality; Software metric; Eclipse; Compiler; Code review; Software engineering; Software development; Source lines of code; Software quality assurance; Static program analysis; Software; Code smell; Data science; Domain (mathematical analysis); Software system; Source code; Software bug; Quality (philosophy); 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":[0.0002712226,0.0000895646,0.00008615219,0.0001041148,0.0000776102,0.00008282274,0.00047301,0.00004355196,0.00003600526],"category_scores_gemma":[0.0002494933,0.0000827765,0.00003586127,0.0002811497,0.00001068481,0.001151424,0.0003153281,0.0001139524,0.00007822757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006414812,"about_ca_system_score_gemma":0.00003530569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000212456,"about_ca_topic_score_gemma":4.363571e-7,"domain_scores_codex":[0.9989547,0.00002347054,0.00009289329,0.000172279,0.0002664708,0.0004902165],"domain_scores_gemma":[0.9989999,0.0003754618,0.00001428021,0.0004129349,0.00003801358,0.0001594041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005371185,0.0002423826,0.4692117,0.0001783827,0.00008593503,0.00006066254,0.009281643,0.1304753,0.00362623,0.28382,0.002997856,0.1000145],"study_design_scores_gemma":[0.0004038422,0.00005108404,0.01990685,0.00006196952,0.000006311498,0.00009896384,0.00006644097,0.9648054,0.008958214,0.003729484,0.001255598,0.0006559048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2129292,0.000193734,0.7855029,0.00001493819,0.0003129507,0.00005136068,1.14651e-7,0.000477825,0.0005170071],"genre_scores_gemma":[0.6886615,0.000001253412,0.3110346,0.00005356066,0.00008768612,0.000004784815,2.21975e-7,0.000008043621,0.0001482727],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.83433,"threshold_uncertainty_score":0.3375528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06928329702945245,"score_gpt":0.2933214175262965,"score_spread":0.2240381204968441,"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."}}