{"id":"W2200054515","doi":"10.1007/s10664-015-9409-1","title":"On the unreliability of bug severity data","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; University of Waterloo","funders":"","keywords":"Computer science; Software bug; Reliability (semiconductor); Eclipse; Software; Data mining; Data science; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001508396,0.0001911941,0.0002281005,0.00009041676,0.00004484664,0.00006778585,0.002972391,0.00008867232,0.00001531772],"category_scores_gemma":[0.02473654,0.0001396855,0.00005722779,0.0008165184,0.00005286242,0.000323957,0.001431701,0.0004592965,0.00006289509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001295937,"about_ca_system_score_gemma":0.000148959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002938743,"about_ca_topic_score_gemma":8.305802e-7,"domain_scores_codex":[0.9979551,0.00006970319,0.0002790659,0.0005092919,0.000784423,0.0004024615],"domain_scores_gemma":[0.9923173,0.004710481,0.00004129711,0.002532578,0.0001466311,0.0002517017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006591679,0.0007469023,0.6372493,0.0003682106,0.0002230379,0.0001085425,0.002233612,0.1803566,0.0001736338,0.008963563,0.159899,0.009611604],"study_design_scores_gemma":[0.001005794,0.0004501552,0.479854,0.0001936899,0.000018646,0.00004494449,0.00002726932,0.4609399,0.002724544,0.004699059,0.04890792,0.001134114],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2803766,0.0001092236,0.7170793,0.001023772,0.0004894519,0.0001739548,0.00001597993,0.0006996978,0.00003201027],"genre_scores_gemma":[0.9626713,0.000002037697,0.03701674,0.0001435517,0.00008573214,0.00001630037,0.00000754623,0.00002382421,0.00003293932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6822947,"threshold_uncertainty_score":0.9834785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1072583466602886,"score_gpt":0.3248063854558618,"score_spread":0.2175480387955732,"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."}}