{"id":"W4251131822","doi":"10.1145/2786763.2694394","title":"Dual Execution for On the Fly Fine Grained Execution Comparison","year":2015,"lang":"en","type":"article","venue":"ACM SIGARCH Computer Architecture News","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Debugging; Reuse; Identification (biology); Distributed computing; Programming language","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":[0.003375202,0.001111677,0.0009119161,0.002393069,0.0007535406,0.001781754,0.002318658,0.0009018866,0.004251848],"category_scores_gemma":[0.01051135,0.0006967889,0.0005666105,0.001639298,0.001655914,0.004685735,0.003911186,0.002053794,0.001176832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001013936,"about_ca_system_score_gemma":0.001451568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001393553,"about_ca_topic_score_gemma":0.001959377,"domain_scores_codex":[0.9950806,0.00134436,0.0004718853,0.00100361,0.001630833,0.0004686817],"domain_scores_gemma":[0.9900599,0.003500711,0.0009068855,0.004062234,0.001151242,0.0003191063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003371603,0.0006160052,0.01466435,0.0006987929,0.0001414911,0.0006834089,0.001608453,0.02831198,0.1526961,0.07603932,0.01016305,0.7110054],"study_design_scores_gemma":[0.0003499329,0.001135264,0.00596244,0.0002347751,0.0001436797,0.001139893,0.0004001901,0.539164,0.2865567,0.1012062,0.06345025,0.0002567426],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03777936,0.000328124,0.943661,0.0001787863,0.0001137634,0.0001950253,0.0002430955,0.01387799,0.003622968],"genre_scores_gemma":[0.431914,0.000115139,0.5626967,0.0001836462,0.00004003445,0.0002776756,0.0004925382,0.002071629,0.002208624],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004251848,"threshold_uncertainty_score":0.01784998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07261865442083672,"score_gpt":0.3080282068405812,"score_spread":0.2354095524197445,"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."}}