{"id":"W2156833313","doi":"10.1145/1368088.1368151","title":"An approach to detecting duplicate bug reports using natural language and execution information","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":544,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Eclipse; Software bug; Natural language; Security bug; Open source; Information retrieval; Natural language processing; Programming language; Software; Information security; Computer security","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":[0.0090852,0.001909179,0.002136565,0.01498157,0.001691331,0.002529733,0.00380367,0.002710235,0.001194723],"category_scores_gemma":[0.04596542,0.001278351,0.002238688,0.005984217,0.001584893,0.004837842,0.00218775,0.002058669,0.0006546177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001791656,"about_ca_system_score_gemma":0.005358882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01189806,"about_ca_topic_score_gemma":0.01472455,"domain_scores_codex":[0.9853231,0.003484261,0.001868142,0.00312103,0.005830804,0.0003725816],"domain_scores_gemma":[0.9296833,0.03111161,0.01546356,0.008280903,0.01470148,0.0007590845],"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":[0.0008712774,0.001389589,0.05807259,0.00199533,0.000660558,0.003458241,0.004696444,0.01228015,0.06748276,0.007841917,0.01020602,0.8310452],"study_design_scores_gemma":[0.0007595714,0.001748164,0.07598227,0.0007097548,0.001856489,0.01709632,0.003391933,0.6428931,0.1636544,0.0339969,0.05646628,0.001444855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0997027,0.001440838,0.8747025,0.001393795,0.0001940751,0.001434549,0.001613436,0.0165717,0.002946519],"genre_scores_gemma":[0.1645165,0.0002812308,0.8308689,0.0004782802,0.0001058948,0.000444035,0.00138276,0.0002790388,0.001643345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01498157,"threshold_uncertainty_score":0.04804766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.018405413256578,"score_gpt":0.2639931120956284,"score_spread":0.2455876988390504,"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."}}