{"id":"W2303463411","doi":"10.1007/s10836-016-5577-1","title":"Exemplar-based Failure Triage for Regression Design Debugging","year":2016,"lang":"en","type":"article","venue":"Journal of Electronic Testing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Debugging; Computer science; Metric (unit); Triage; Flexibility (engineering); Process (computing); Reliability engineering; Data mining; Engineering; Programming language; Mathematics","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":[0.001958028,0.0001043245,0.0001646927,0.0001492867,0.0001612856,0.00008782197,0.0005553393,0.00004581204,0.000003939205],"category_scores_gemma":[0.003448311,0.00006089995,0.00007269678,0.0002419917,0.00001008107,0.0004683429,0.00002894399,0.0002112809,0.000002825046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001369276,"about_ca_system_score_gemma":0.0005355097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001364432,"about_ca_topic_score_gemma":0.000001210608,"domain_scores_codex":[0.9987382,0.0001620002,0.0003595089,0.0001740501,0.0002191287,0.0003471355],"domain_scores_gemma":[0.9969754,0.001810458,0.00067299,0.0002482615,0.000222423,0.000070472],"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":[0.0001419283,0.00008267257,0.002144316,0.00003310907,0.00003394555,0.0000166733,0.00009239998,0.002652212,0.1967585,0.01014349,0.005402566,0.7824982],"study_design_scores_gemma":[0.007349538,0.003848874,0.002995775,0.001875858,0.00009141905,0.0006907676,0.00002578541,0.8615492,0.04038938,0.0308946,0.04962106,0.0006677459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004333054,0.000240689,0.9882252,0.006894918,0.00008792771,0.0000993737,4.463207e-7,0.00007338981,0.00004496916],"genre_scores_gemma":[0.7337514,0.000001584733,0.2659965,0.00006887845,0.0001170107,0.000004402762,4.492615e-7,0.000009191725,0.00005055842],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.858897,"threshold_uncertainty_score":0.4128199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05114569072665122,"score_gpt":0.2914108569765113,"score_spread":0.2402651662498601,"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."}}