{"id":"W2001599472","doi":"10.1007/s11219-010-9128-1","title":"An industrial case study of classifier ensembles for locating software defects","year":2011,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Sabancı Üniversitesi","keywords":"Computer science; Software; Classifier (UML); False alarm; Software quality; Data mining; Domain (mathematical analysis); Ensemble learning; Embedded software; Machine learning; Artificial intelligence; Reliability engineering; Software development; Engineering; Operating system","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":[0.003925539,0.000281374,0.0004755127,0.0003610355,0.0004718913,0.0002332665,0.001397548,0.0002070321,0.00002658641],"category_scores_gemma":[0.007430844,0.0002622787,0.0001808591,0.0005939433,0.00007773716,0.000916869,0.000243889,0.0007916695,0.000004409028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000133697,"about_ca_system_score_gemma":0.0004771345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004931234,"about_ca_topic_score_gemma":0.0001212732,"domain_scores_codex":[0.9963475,0.0006729981,0.0009515778,0.0005312333,0.0008323308,0.0006642903],"domain_scores_gemma":[0.9945363,0.002716269,0.00046134,0.001022082,0.0008179394,0.0004460883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001979104,0.002548217,0.74652,0.0002102876,0.0002965702,0.002368192,0.04157648,0.000672715,0.0002611104,0.0005468196,0.0007777147,0.2040239],"study_design_scores_gemma":[0.06984302,0.06352174,0.5410385,0.002235792,0.0009475328,0.07507647,0.1468926,0.01248893,0.03082224,0.0439406,0.001575097,0.01161748],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5301688,0.00004155021,0.4687733,0.000007229631,0.0004666298,0.00032942,0.000006097092,0.0002042337,0.000002689392],"genre_scores_gemma":[0.8502163,0.000001551069,0.1493643,0.00002546719,0.0003000463,0.00003866416,0.000001643131,0.0000359895,0.00001611911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3200474,"threshold_uncertainty_score":0.999983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2236840213549557,"score_gpt":0.3779922822970453,"score_spread":0.1543082609420896,"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."}}