{"id":"W2100060170","doi":"10.1109/icstw.2009.18","title":"A Mutation/Injection-Based Automatic Framework for Evaluating Code Clone Detection Tools","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":195,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"clone (Java method); Computer science; Benchmark (surveying); Precision and recall; Software; Software maintenance; Code (set theory); Data mining; Mutation; Machine learning; Software system; Software engineering; Artificial intelligence; Programming language; Set (abstract data type); Biology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01994338,0.002616291,0.002855642,0.01751186,0.001596845,0.003082383,0.003738937,0.002714063,0.001195493],"category_scores_gemma":[0.07022418,0.0009755414,0.001659491,0.005556416,0.002212218,0.003982276,0.002311287,0.001559791,0.0005798037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002693595,"about_ca_system_score_gemma":0.004264296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007365448,"about_ca_topic_score_gemma":0.006592975,"domain_scores_codex":[0.9709384,0.007983164,0.003164149,0.00302515,0.01407393,0.0008152773],"domain_scores_gemma":[0.9268469,0.03199418,0.013774,0.008965603,0.01755299,0.0008664107],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008919647,0.002069632,0.07359952,0.001166571,0.0007219765,0.0003585666,0.001021342,0.1262826,0.09522365,0.01527723,0.004563761,0.6788232],"study_design_scores_gemma":[0.0002336214,0.002374292,0.03644548,0.0001408255,0.0002273231,0.0007895927,0.0002045107,0.8889894,0.06052713,0.005882257,0.003855824,0.0003297729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09782159,0.0005556922,0.8786755,0.0001362683,0.00003601533,0.001573727,0.0007497207,0.01828751,0.002164036],"genre_scores_gemma":[0.2743351,0.00009363458,0.7227397,0.00005845872,0.00002095418,0.001119538,0.0009037649,0.0002931019,0.0004356404],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9800566,"threshold_uncertainty_score":0.105472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05236989384220891,"score_gpt":0.360897314909121,"score_spread":0.3085274210669121,"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."}}