{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00297114,0.001353158,0.001562077,0.003614282,0.0009651028,0.001738588,0.00270655,0.001545104,0.002240349],"category_scores_gemma":[0.01135423,0.0007248331,0.00151839,0.001754213,0.001377041,0.002991906,0.002051211,0.002166996,0.0009986107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001530739,"about_ca_system_score_gemma":0.002341881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0063507,"about_ca_topic_score_gemma":0.007863352,"domain_scores_codex":[0.9962029,0.0009434961,0.0002879591,0.0008140957,0.00134048,0.0004109773],"domain_scores_gemma":[0.9925812,0.002985082,0.001395439,0.00180454,0.001004222,0.0002295396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003980705,0.0002072915,0.007301721,0.0002863,0.0001178854,0.0003194989,0.0005924584,0.4718352,0.01842427,0.03030361,0.004429848,0.4657838],"study_design_scores_gemma":[0.0000140727,0.00007259852,0.0004413065,0.00002667652,0.00002166785,0.0001108181,0.00003822898,0.9725928,0.01078568,0.01399787,0.00187144,0.00002677082],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007720103,0.0001554716,0.9863187,0.00009262186,0.00001375826,0.00005164793,0.0000696428,0.005299747,0.0002784501],"genre_scores_gemma":[0.3565029,0.0002073695,0.640694,0.0001506447,0.00004321834,0.000136874,0.0004415908,0.0005521491,0.001271218],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0063507,"threshold_uncertainty_score":0.0157131,"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."}}