{"id":"W2888049099","doi":"10.1007/s10664-018-9643-4","title":"Preventing duplicate bug reports by continuously querying bug reports","year":2018,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Mitacs; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data deduplication; Software bug; BitTorrent tracker; Search engine indexing; Security bug; Information retrieval; Software; Database; Artificial intelligence; Cloud computing; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001369462,0.0005076992,0.0005380542,0.0002911093,0.0002703097,0.0004254489,0.0008894708,0.0002522566,0.00005578436],"category_scores_gemma":[0.007395887,0.0005329254,0.0002145895,0.001291467,0.00008458356,0.0007414448,0.000897226,0.0007033354,0.00009016115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002696202,"about_ca_system_score_gemma":0.0001278586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000068204,"about_ca_topic_score_gemma":0.000002100943,"domain_scores_codex":[0.9952132,0.00005393223,0.001009628,0.001389871,0.0009896115,0.00134375],"domain_scores_gemma":[0.9960524,0.001113515,0.0002617465,0.001732311,0.0003055102,0.0005344505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001100678,0.0002409953,0.8939093,0.0003052698,0.0002238034,0.003887044,0.001234978,0.004383156,0.01049074,0.00005834772,0.07383335,0.01142199],"study_design_scores_gemma":[0.001172358,0.0007584217,0.3292599,0.001191394,0.00008515326,0.00795668,0.00002842206,0.0532077,0.07061291,0.001131226,0.5293427,0.005253118],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.342963,0.0004812257,0.6514064,0.0002635789,0.001318657,0.0003175354,0.00000196724,0.003190319,0.00005732326],"genre_scores_gemma":[0.9274199,0.000007716735,0.07069585,0.0001842353,0.0006259844,0.00011977,0.00001403911,0.0001256973,0.000806783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.584457,"threshold_uncertainty_score":0.9997122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0147943302507017,"score_gpt":0.2740173627620474,"score_spread":0.2592230325113457,"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."}}