# Generalizability of Code Clone Detection on CodeBERT

arXiv: https://arxiv.org/abs/2208.12588 · HTML: https://mlsanity.com/paper/2208.12588/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 26 Aug 2022.

## Builds on (most cited first, 6 of 6)

- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree](https://mlsanity.com/paper/2002.08653/) (2020)
- [Oreo: Detection of Clones in the Twilight Zone](https://mlsanity.com/paper/1806.05837/) (2018)
- [DeepClone: Modeling Clones to Generate Code Predictions](https://mlsanity.com/paper/2007.11671/) (2020)

## Built on by (most cited first, 4 of 4)

- [Investigating the Efficacy of Large Language Models for Code Clone Detection](https://mlsanity.com/paper/2401.13802/) (2024)
- [Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization](https://mlsanity.com/paper/2508.02840/) (2025)
- [Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection](https://mlsanity.com/paper/2605.02860/) (2026)
- [Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning](https://mlsanity.com/paper/2609.17338/) (2026)

## Abstract (arXiv)

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. We show that the generalizability of CodeBERT decreases by evaluating two different subsets of Java code clones from BigCloneBench. We observe a significant drop in F1 score when we evaluate different code snippets and functionality IDs than those used for model building.