{"id":"W2007818470","doi":"10.5555/2662708.2662710","title":"A mutation analysis based benchmarking framework for clone detectors","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Saskatchewan","funders":"","keywords":"Benchmarking; Benchmark (surveying); Granularity; clone (Java method); Computer science; Detector; Mutation testing; Mutation; Data mining; Software engineering; Operating system; Biology; Genetics; Telecommunications; Business; Gene; Cartography; Geography","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":[0.01938788,0.002004934,0.002035043,0.008636074,0.00105669,0.003725623,0.004716104,0.002430047,0.001947271],"category_scores_gemma":[0.04334399,0.000706022,0.001357038,0.003603715,0.001618548,0.003785677,0.002664207,0.001905095,0.0006259677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002501464,"about_ca_system_score_gemma":0.003201418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004795802,"about_ca_topic_score_gemma":0.003229339,"domain_scores_codex":[0.9791915,0.009357635,0.001677912,0.002132505,0.006690728,0.0009497524],"domain_scores_gemma":[0.9712669,0.01194281,0.003430116,0.00498488,0.007461697,0.0009136045],"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":[0.0008950399,0.001370277,0.02769462,0.0008275441,0.0004429618,0.0007916025,0.0007496164,0.3002535,0.05059547,0.08320578,0.009201401,0.5239722],"study_design_scores_gemma":[0.00003886331,0.0002998049,0.002218698,0.00008833821,0.00005274609,0.0002253337,0.00006272684,0.9619203,0.01605354,0.01534767,0.00362596,0.00006595242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0403532,0.0005063274,0.9380227,0.0002559577,0.00005827937,0.0003796045,0.0003125218,0.01743189,0.002679422],"genre_scores_gemma":[0.4525177,0.0001866934,0.543695,0.0001412499,0.00004141095,0.0004200601,0.0009740298,0.001154176,0.0008698163],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01938788,"threshold_uncertainty_score":0.1025342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01504557180058474,"score_gpt":0.2753145520658611,"score_spread":0.2602689802652763,"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."}}