{"id":"W2129377409","doi":"10.1109/icsm.2015.7332456","title":"An empirical study of bugs in test code","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Software bug; Computer science; Code (set theory); Test (biology); Root cause; Regression testing; Code coverage; Programming language; Software; Reliability engineering; Software development; Engineering; Biology","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":[0.0004404304,0.00004323584,0.00008197305,0.000114224,0.000006356765,0.00002681814,0.0006464857,0.00001960182,0.000004006039],"category_scores_gemma":[0.0006642123,0.0000362956,0.000006387919,0.0004797983,0.00001145272,0.0001699104,0.000154665,0.00008173785,0.00002031661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003141055,"about_ca_system_score_gemma":0.00007072641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001953621,"about_ca_topic_score_gemma":0.0001251441,"domain_scores_codex":[0.9992349,0.00003440239,0.0001114328,0.0001676494,0.0003155829,0.0001360034],"domain_scores_gemma":[0.9989985,0.0003689586,0.000008831453,0.0004469631,0.00006960988,0.000107122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001228466,0.0006509788,0.9946142,0.000001564467,0.000001183353,0.00001551479,0.002008876,0.0008647392,0.00006282714,0.00006700701,0.0006457394,0.001066149],"study_design_scores_gemma":[0.0006480252,0.001103669,0.9046319,0.000003099299,4.152102e-7,0.000003227553,0.000340976,0.09247381,0.0004447263,0.0001405057,0.0001303187,0.00007934973],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9423809,0.000006826974,0.05701376,0.0001049679,0.0000468271,0.00009781923,2.167416e-7,0.000122862,0.0002258237],"genre_scores_gemma":[0.9900063,1.124806e-7,0.009887294,0.00001905474,0.0000107607,0.000006153665,1.198039e-7,0.00000352998,0.00006672474],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09160908,"threshold_uncertainty_score":0.1480092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08033739344236439,"score_gpt":0.3817909511334575,"score_spread":0.3014535576910931,"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."}}