{"id":"W3011074760","doi":"10.1109/mtv48867.2019.00009","title":"Expediting Design Bug Discovery in Regressions of x86 Processors Using Machine Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"VLSI and Analog Circuit Testing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Debugging; Computer science; Expediting; x86; Leverage (statistics); Overhead (engineering); Embedded system; Software bug; Operating system; Machine learning; 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":[0.0004512049,0.0001015936,0.0001761248,0.0001517397,0.00007569741,0.00007609984,0.0003848972,0.00003771044,0.00001374303],"category_scores_gemma":[0.0002474904,0.00008290845,0.00003574326,0.0004977103,0.00001696611,0.0009006262,0.0001650132,0.0001868996,0.000006842148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002576028,"about_ca_system_score_gemma":0.00008832441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002156931,"about_ca_topic_score_gemma":0.00001030757,"domain_scores_codex":[0.9989237,0.00008915308,0.0002649127,0.0002754548,0.0001980311,0.0002487399],"domain_scores_gemma":[0.9992834,0.0002795054,0.0001630673,0.0001966921,0.00003997693,0.0000374033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001611287,0.0001731686,0.7024599,0.0001737157,0.00001325093,0.00004205987,0.003244229,0.1090718,0.1449867,0.005460175,0.00001665943,0.03435666],"study_design_scores_gemma":[0.00024287,0.00005992845,0.001779482,0.0004232783,0.000002264335,0.00001273756,0.0002798265,0.9828304,0.01372807,0.0004644717,0.00001054137,0.0001661357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.486341,0.00008973321,0.5119963,0.00003060094,0.00006901977,0.00007696477,1.855424e-7,0.00006185465,0.001334315],"genre_scores_gemma":[0.9829157,0.00000350139,0.01657225,0.00003315534,0.00002879999,0.000001985979,6.782523e-7,0.000008278247,0.0004356292],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8737586,"threshold_uncertainty_score":0.3380908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04276156810023777,"score_gpt":0.2631641248513293,"score_spread":0.2204025567510915,"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."}}