{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003452252,0.00114013,0.0009266257,0.002393006,0.0007454317,0.001790499,0.002366785,0.0009133831,0.004392032],"category_scores_gemma":[0.01081047,0.0007245999,0.0005883513,0.001644358,0.001689608,0.004685779,0.004106133,0.002070581,0.001194336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001002638,"about_ca_system_score_gemma":0.0014532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001410164,"about_ca_topic_score_gemma":0.002000622,"domain_scores_codex":[0.9948931,0.001405719,0.0004969561,0.001053921,0.001663389,0.0004869337],"domain_scores_gemma":[0.9896542,0.003713653,0.0009292654,0.004215097,0.00115439,0.0003333089],"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":[0.003489928,0.0006096875,0.01475687,0.0007420352,0.0001418247,0.0006879778,0.001690736,0.02961931,0.1490419,0.07498483,0.009890091,0.7143448],"study_design_scores_gemma":[0.0003598454,0.0011519,0.006088391,0.0002438273,0.0001511768,0.001134807,0.0004070853,0.5371127,0.2849556,0.1018713,0.06626252,0.0002609394],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03582684,0.0003100952,0.9457643,0.000165767,0.0001047415,0.0001971815,0.0002520751,0.01395717,0.00342178],"genre_scores_gemma":[0.4204215,0.0001126057,0.5741423,0.0001726224,0.0000387908,0.0002867753,0.0005075591,0.002151161,0.00216665],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004392032,"threshold_uncertainty_score":0.0182575,"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."}}