{"id":"W1024906986","doi":"10.1007/s10664-015-9387-3","title":"A contextual approach towards more accurate duplicate bug report detection and ranking","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data deduplication; Software bug; Android (operating system); Software; Ranking (information retrieval); Context (archaeology); Data science; Software engineering; Data mining; World Wide Web; Information retrieval; Database","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":[0.0008912401,0.0003223351,0.0003470919,0.0002500158,0.00009526451,0.0002795768,0.0006283331,0.0001741639,0.000002051962],"category_scores_gemma":[0.005311671,0.0003100477,0.00008355189,0.0008644225,0.00004947561,0.0005899671,0.0005696282,0.0005350605,0.00001697916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002241492,"about_ca_system_score_gemma":0.000120056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005147979,"about_ca_topic_score_gemma":7.393114e-7,"domain_scores_codex":[0.9974777,0.00003774341,0.0003906593,0.000756218,0.0007017214,0.000635954],"domain_scores_gemma":[0.9980202,0.0004887518,0.00007024991,0.000699261,0.0001954299,0.0005261325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002070368,0.0006498655,0.3816082,0.001176672,0.0007486867,0.004422944,0.01739177,0.3535842,0.004590458,0.0007169185,0.006172817,0.2287305],"study_design_scores_gemma":[0.001988021,0.0002583706,0.2692412,0.000104033,0.00002935068,0.003389636,0.00008641437,0.6979429,0.003702894,0.0002270546,0.02147916,0.001551035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2246357,0.0003406931,0.7725818,0.0002193795,0.0003469143,0.0002142841,0.00000143495,0.001632297,0.00002757875],"genre_scores_gemma":[0.9243937,0.000005600996,0.07508279,0.00007607759,0.0001985213,0.0001005238,0.000005834961,0.0000507888,0.0000861686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6997581,"threshold_uncertainty_score":0.9999352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05477320630831465,"score_gpt":0.3061968965378645,"score_spread":0.2514236902295499,"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."}}