{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009202563,0.001979626,0.001679288,0.009162541,0.001046849,0.003375327,0.002453545,0.002523768,0.002541283],"category_scores_gemma":[0.03841531,0.0009388175,0.003627196,0.005656901,0.001151689,0.005300748,0.001746082,0.00208383,0.0008462512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002017419,"about_ca_system_score_gemma":0.001047132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01151101,"about_ca_topic_score_gemma":0.007998476,"domain_scores_codex":[0.99625,0.001902989,0.000268042,0.0009126113,0.0004331418,0.0002332719],"domain_scores_gemma":[0.9445788,0.04899444,0.002892058,0.001323268,0.001783675,0.0004277641],"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":[0.0007689425,0.0006353172,0.1236803,0.001004598,0.001328854,0.0007501006,0.006386603,0.4942843,0.003987483,0.08440358,0.01171839,0.2710514],"study_design_scores_gemma":[0.00004173012,0.00006208135,0.006602032,0.00005028091,0.0001318744,0.0001357065,0.0002406235,0.9578302,0.0003365573,0.03302689,0.0015023,0.00003982022],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2037297,0.00220042,0.7860281,0.001725284,0.0001707742,0.0003701217,0.001863691,0.001730596,0.00218125],"genre_scores_gemma":[0.8926523,0.001386347,0.09932383,0.0001865395,0.0003437185,0.0007823244,0.003130511,0.0003009947,0.001893451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01151101,"threshold_uncertainty_score":0.04866844,"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."}}