{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002946224,0.00008143664,0.00009018036,0.0001242965,0.00005694357,0.00002998525,0.0005878718,0.00003680728,0.00002466212],"category_scores_gemma":[0.0009766342,0.00003806759,0.00004557193,0.0004055546,0.00004298195,0.0001073157,0.00006596719,0.00004189334,0.00001454918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002063172,"about_ca_system_score_gemma":0.00003632062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003165769,"about_ca_topic_score_gemma":8.493757e-7,"domain_scores_codex":[0.9992709,0.00004230853,0.0001289078,0.000173421,0.0002633294,0.0001211079],"domain_scores_gemma":[0.9956982,0.003458197,0.0001024194,0.0006104679,0.00009989183,0.00003086673],"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":[0.00002671305,0.0005042994,0.1533113,0.00001932217,0.000018641,0.00001373201,0.0002506915,0.0006982478,0.003081437,0.02836249,0.006342259,0.8073709],"study_design_scores_gemma":[0.001426595,0.001113143,0.3740443,0.0003747538,0.00005205271,0.000005906132,0.000005029557,0.3903666,0.185876,0.04306932,0.002707097,0.000959159],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06330255,0.000004649052,0.9326355,0.0007897985,0.0001188384,0.0001578836,0.000002926032,0.002780123,0.0002077692],"genre_scores_gemma":[0.9626424,5.260736e-7,0.03669722,0.0004949332,0.000009762145,0.00002865587,4.823403e-7,0.000005683763,0.0001203075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8993399,"threshold_uncertainty_score":0.1552351,"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."}}