{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003222515,0.00007703734,0.000123788,0.0004756057,0.00004961841,0.00005411808,0.0001809381,0.0001519737,0.000001299877],"category_scores_gemma":[0.0003981228,0.00007468126,0.00001552046,0.0003573652,0.0000552717,0.0007365724,0.00004872829,0.00009038405,0.000002934776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002542019,"about_ca_system_score_gemma":0.00003851436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003959616,"about_ca_topic_score_gemma":5.346497e-7,"domain_scores_codex":[0.9992905,0.000009223833,0.0002847312,0.0001598781,0.0001242545,0.0001314519],"domain_scores_gemma":[0.9990613,0.0001248737,0.0001605542,0.0004625632,0.000153216,0.00003748982],"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":[0.00001161626,0.00005141216,0.07777274,0.0006869151,0.00001528975,4.650976e-7,0.0003754315,0.001187224,0.004587677,0.005794777,0.00002879844,0.9094877],"study_design_scores_gemma":[0.0003773706,0.0002511001,0.0761706,0.00001421133,0.000003605144,0.00005346641,0.00004788191,0.9158383,0.005101488,0.001371293,0.0006451812,0.0001255196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3480705,0.0000164008,0.650883,0.00007324042,0.00003628243,0.0003220355,0.000001131681,0.0005872493,0.00001020209],"genre_scores_gemma":[0.8704654,0.000002387859,0.1293829,0.00002297797,0.000002588398,0.0001035216,0.00001267107,0.000004084831,0.000003513002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.914651,"threshold_uncertainty_score":0.3045413,"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."}}