{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002488884,0.00006186896,0.00005724174,0.0001449602,0.0001166543,0.0001121835,0.0001491523,0.00002769319,5.578729e-7],"category_scores_gemma":[0.0002050789,0.00005669791,0.00001057566,0.0003303216,0.00001081102,0.001272634,0.0001158909,0.0000958044,0.000003582147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004425009,"about_ca_system_score_gemma":0.00002119034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001576611,"about_ca_topic_score_gemma":6.854319e-7,"domain_scores_codex":[0.9993237,0.00001247589,0.0001288503,0.0001652812,0.0002005264,0.0001692173],"domain_scores_gemma":[0.9994828,0.00003801937,0.00002906825,0.0003106919,0.0000530589,0.00008635505],"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":[0.00004016091,0.0002370627,0.1508957,0.0003371957,0.00006492489,0.0004411375,0.1042659,0.07989147,0.2043815,0.002742796,0.0006535749,0.4560486],"study_design_scores_gemma":[0.00007831302,0.00002660249,0.07938124,0.000006613232,9.234465e-7,0.001335873,0.0001627463,0.9095296,0.009251462,0.00001322672,0.00005546892,0.0001579554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5320555,0.00001512623,0.4675219,0.000009109294,0.0000425202,0.00007054261,5.486109e-8,0.0001925743,0.00009268],"genre_scores_gemma":[0.8328769,4.835031e-7,0.1670359,0.00003973225,0.00002029182,0.000005441841,0.000001674438,0.00000312386,0.0000164777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8296381,"threshold_uncertainty_score":0.2312074,"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."}}