{"id":"W4243778460","doi":"10.1145/2775054.2694394","title":"Dual Execution for On the Fly Fine Grained Execution Comparison","year":2015,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Debugging; Programming language; Distributed computing","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":[0.0008287381,0.0001460571,0.0001546523,0.00007737436,0.0001985598,0.0001838448,0.0009173615,0.00006826266,0.000001998769],"category_scores_gemma":[0.003230011,0.000100554,0.00004849205,0.0002170524,0.00004942162,0.0002136487,0.0001818241,0.0001229847,0.00003159447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004273546,"about_ca_system_score_gemma":0.0000508453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009894738,"about_ca_topic_score_gemma":0.00002072277,"domain_scores_codex":[0.9988507,0.00008906463,0.0002087275,0.000305657,0.0002984345,0.0002474005],"domain_scores_gemma":[0.9969852,0.001839324,0.0001534941,0.0008023139,0.0001392801,0.00008037899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001301381,0.0002330028,0.004152354,0.00003314991,0.00003217731,0.00001062674,0.003377726,0.0005880873,0.0003132472,0.08278324,0.8689231,0.03942316],"study_design_scores_gemma":[0.002095657,0.003692618,0.009190445,0.0003328668,0.000083249,0.00004786291,0.0002393388,0.4752088,0.01649473,0.4426955,0.04874946,0.001169428],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2111591,0.0002549255,0.750595,0.02013261,0.001545728,0.001103358,0.00002509059,0.01267463,0.002509658],"genre_scores_gemma":[0.9101549,6.248532e-7,0.08891773,0.0005759532,0.0001755762,0.00005871162,0.00002184598,0.000009402792,0.00008524777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8201736,"threshold_uncertainty_score":0.4100472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1316643127859867,"score_gpt":0.3284666110387123,"score_spread":0.1968022982527256,"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."}}