Generalizability of Code Clone Detection on CodeBERT
Tim Sonnekalb, Bernd Gruner, Clemens-Alexander Brust, Patrick Mäder
Abstract
Transformer networks such as CodeBERT already achieve outstanding results for code clone detection in benchmark datasets, so one could assume that this task has already been solved. However, code clone detection is not a trivial task. Semantic code clones, in particular, are challenging to detect.
Topics & Concepts
Generalizability theoryComputer scienceclone (Java method)Benchmark (surveying)Code (set theory)Task (project management)Programming languageEngineeringMathematicsBiologyGeneSet (abstract data type)Systems engineeringBiochemistryStatisticsGeographyGeodesySoftware Engineering ResearchAdvanced Malware Detection TechniquesSoftware System Performance and Reliability