{"id":"W2772234823","doi":"10.1109/tcad.2017.2783303","title":"Failure Triage in RTL Regression Verification","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","topic":"VLSI and Analog Circuit Testing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Debugging; Computer science; Root cause; Ranking (information retrieval); Overhead (engineering); Data mining; Triage; Cluster analysis; Root (linguistics); Root cause analysis; Reliability engineering; Machine learning; Programming language; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008382946,0.000281089,0.0004935843,0.0003985295,0.0004832939,0.0005467034,0.0009288513,0.0001934072,0.00000355094],"category_scores_gemma":[0.00003160177,0.00023044,0.00009051939,0.0003186793,0.00009094581,0.0006948572,0.000005092003,0.0003693691,0.00000817842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008374329,"about_ca_system_score_gemma":0.0001315472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004438128,"about_ca_topic_score_gemma":0.00002338847,"domain_scores_codex":[0.9977863,0.0003338674,0.0006681951,0.0005921684,0.0003136626,0.0003057848],"domain_scores_gemma":[0.9978989,0.0002893283,0.000476925,0.0009979645,0.0002133965,0.0001234776],"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":[0.000009779085,0.0003678025,0.0002987607,0.0001655604,0.00006946307,0.00007997826,0.001129864,0.03090798,0.05347807,0.00286197,0.0002446458,0.9103861],"study_design_scores_gemma":[0.001433288,0.0004612356,0.001447595,0.001397474,0.0000196124,0.0001068614,0.0001287191,0.9830866,0.01116702,0.0002508335,0.00009814199,0.0004026513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02179092,0.000127009,0.9761432,0.0001079239,0.001076884,0.0004557335,0.00001083198,0.0001298502,0.0001576116],"genre_scores_gemma":[0.9979161,0.00004194969,0.001829749,0.00002505847,0.0000460114,0.00003907526,0.000002059648,0.00001681437,0.00008319058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9761252,"threshold_uncertainty_score":0.939707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05604785648069878,"score_gpt":0.2647481906978063,"score_spread":0.2087003342171075,"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."}}