{"id":"W1999910737","doi":"10.1109/msr.2013.6624026","title":"A contextual approach towards more accurate duplicate bug report detection","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":129,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data deduplication; Software bug; BitTorrent tracker; Security bug; Software regression; Vocabulary; Software; Context (archaeology); Android (operating system); Debugging; Data science; World Wide Web; Software engineering; Software quality; Software development; Artificial intelligence; Database; Computer security; Software security assurance; Information security; Eye tracking","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":[0.0003380918,0.0001331309,0.0001343405,0.0001190405,0.00007042292,0.0002848388,0.0007283965,0.00007180302,0.00004946558],"category_scores_gemma":[0.0004861558,0.0001083064,0.00005495454,0.0004820419,0.00003923916,0.0006310696,0.0003275695,0.000201237,0.0003395521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006475858,"about_ca_system_score_gemma":0.00006302294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006261569,"about_ca_topic_score_gemma":0.00000228458,"domain_scores_codex":[0.9985242,0.00002350172,0.0002209333,0.0004696492,0.0003994462,0.0003622148],"domain_scores_gemma":[0.9986321,0.0001169972,0.00004619245,0.0008430765,0.0002065127,0.0001551474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001772189,0.0004220265,0.008577785,0.0001634926,0.0002072877,0.0004183287,0.002435571,0.003432945,0.03591191,0.006966904,0.02418214,0.9172639],"study_design_scores_gemma":[0.0005417724,0.0001311962,0.1990749,0.00001062208,0.000004792035,0.001238769,0.0001093748,0.7595701,0.03299676,0.0007032588,0.00501068,0.0006077684],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1162872,0.00002069286,0.8793004,0.0005959313,0.0001646877,0.000326976,2.613467e-7,0.0008871075,0.002416803],"genre_scores_gemma":[0.9655058,0.000002043304,0.0313374,0.00009225184,0.00006225365,0.0002230244,0.00000208639,0.00001348503,0.002761646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9166561,"threshold_uncertainty_score":0.4416609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02898033520437638,"score_gpt":0.277534679319666,"score_spread":0.2485543441152896,"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."}}