{"id":"W1586383135","doi":"10.1109/latw.2015.7102521","title":"Exemplar-based failure triage for regression design debugging","year":2015,"lang":"en","type":"article","venue":"","topic":"VLSI and Analog Circuit Testing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Debugging; Metric (unit); Triage; Flexibility (engineering); Process (computing); Data mining; Software bug; Reliability engineering; Cluster analysis; Machine learning; Programming language; Software; Engineering","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":[0.001301709,0.001137648,0.001508287,0.004636922,0.0009012158,0.001077499,0.003119393,0.001507982,0.001868921],"category_scores_gemma":[0.007753395,0.000479846,0.0009972265,0.003492877,0.0007913607,0.001707885,0.001896096,0.00158083,0.001219006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006586949,"about_ca_system_score_gemma":0.0007353107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002477518,"about_ca_topic_score_gemma":0.003579928,"domain_scores_codex":[0.9983948,0.0003150191,0.0001179318,0.0003894203,0.0006399336,0.0001427902],"domain_scores_gemma":[0.9963173,0.001199938,0.000699447,0.0007906191,0.0008347735,0.0001580154],"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":[0.0004341947,0.0004106194,0.01664151,0.0003567118,0.0002002677,0.0006414251,0.0006478062,0.3256752,0.02079887,0.01907922,0.008448596,0.6066656],"study_design_scores_gemma":[0.0000101776,0.00006119275,0.001075757,0.0000148501,0.00001750851,0.0002951474,0.00007764541,0.9824237,0.006927276,0.006908931,0.002168402,0.00001944895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01751295,0.0001584613,0.9793687,0.0000939543,0.00001900502,0.00006607403,0.0001933217,0.002100174,0.0004872967],"genre_scores_gemma":[0.326641,0.0001914608,0.6705544,0.00009670468,0.000040323,0.0001394751,0.001172759,0.0001955171,0.0009683648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004636922,"threshold_uncertainty_score":0.006884158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1467957928144607,"score_gpt":0.3005540975466254,"score_spread":0.1537583047321647,"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."}}