{"id":"W2562367443","doi":"10.22360/summersim.2016.scsc.019","title":"On Simulation-based Metrics that Characterize the Behavior of RTL Errors","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Debugging; Debugger; Process (computing); Pruning; Software bug; Programming language; Reliability engineering; Software","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":[0.005268506,0.001843851,0.00102692,0.005995656,0.0004335381,0.001606169,0.0009041736,0.00110978,0.0009908528],"category_scores_gemma":[0.05163591,0.0004455727,0.0007963793,0.004109781,0.001477323,0.002676008,0.0009760658,0.001270528,0.0003732156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001336284,"about_ca_system_score_gemma":0.001338177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002173913,"about_ca_topic_score_gemma":0.002437016,"domain_scores_codex":[0.991963,0.002803318,0.0006297118,0.0007926411,0.003494063,0.0003172141],"domain_scores_gemma":[0.9451517,0.03265366,0.009773819,0.006784863,0.005168133,0.0004677584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003223093,0.0004183238,0.04266626,0.0004713305,0.0002974351,0.0002232116,0.0004199217,0.7731898,0.03100536,0.02919314,0.001019274,0.1207736],"study_design_scores_gemma":[0.00001820684,0.000516389,0.01242987,0.00009966867,0.00004993503,0.0004083951,0.00008388887,0.9600515,0.01503551,0.009310196,0.001933939,0.00006254386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.173267,0.0006399481,0.8195915,0.0001957874,0.00003453866,0.0002451124,0.0005663341,0.002180076,0.003279649],"genre_scores_gemma":[0.7797443,0.0004393938,0.2172124,0.00008198062,0.00003059416,0.0003344308,0.001114863,0.0003897082,0.0006524871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005995656,"threshold_uncertainty_score":0.02786285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06359309796219473,"score_gpt":0.2986554842451256,"score_spread":0.2350623862829308,"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."}}