{"id":"W2945475639","doi":"10.1016/j.infsof.2019.05.007","title":"An HMM-based approach for automatic detection and classification of duplicate bug reports","year":2019,"lang":"en","type":"article","venue":"Information and Software Technology","topic":"Software Engineering Research","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Software regression; Computer science; Software bug; Precision and recall; Hidden Markov model; Software; Rank (graph theory); Crash; Data mining; Information retrieval; Artificial intelligence; Software quality; Software development; Programming language","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":[0.001807679,0.000739208,0.001331207,0.003330063,0.0007422217,0.001496863,0.00151259,0.001516418,0.001799761],"category_scores_gemma":[0.005292508,0.0004582389,0.001014387,0.002322952,0.00038653,0.001274122,0.001092116,0.001369592,0.001932052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005919783,"about_ca_system_score_gemma":0.001581373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007389016,"about_ca_topic_score_gemma":0.01000553,"domain_scores_codex":[0.998104,0.0003364125,0.0001911806,0.0005173536,0.0006594343,0.0001915839],"domain_scores_gemma":[0.9950796,0.001843859,0.0004906863,0.000686411,0.001685164,0.000214166],"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":[0.001006671,0.0005729549,0.03301742,0.0005957547,0.0005126864,0.0007206491,0.0006134415,0.01643183,0.1089446,0.002331426,0.01064569,0.8246068],"study_design_scores_gemma":[0.00008316465,0.0004502219,0.0381167,0.0001018519,0.0004603356,0.001490701,0.0003219093,0.8915547,0.05364733,0.005557979,0.008026667,0.0001884356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09257045,0.00105701,0.8903319,0.0003201118,0.0002432019,0.0002661428,0.001881069,0.011435,0.001895165],"genre_scores_gemma":[0.5676599,0.0006169489,0.4217375,0.0002229847,0.0001499404,0.0002789471,0.003320161,0.0003562283,0.005657458],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007389016,"threshold_uncertainty_score":0.01469201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01059367975443223,"score_gpt":0.2446091503613171,"score_spread":0.2340154706068849,"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."}}