# COSET: A Benchmark for Evaluating Neural Program Embeddings

arXiv: https://arxiv.org/abs/1905.11445 · HTML: https://mlsanity.com/paper/1905.11445/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2019.

## Built on by (most cited first, 10 of 10)

- [The Stack: 3 TB of permissively licensed source code](https://mlsanity.com/paper/2211.15533/) (2022)
- [Generating Adversarial Computer Programs using Optimized Obfuscations](https://mlsanity.com/paper/2103.11882/) (2021)
- [Memorization and Generalization in Neural Code Intelligence Models](https://mlsanity.com/paper/2106.08704/) (2021)
- [VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning](https://mlsanity.com/paper/2112.02650/) (2021)
- [Towards Making Deep Learning-based Vulnerability Detectors Robust](https://mlsanity.com/paper/2108.00669/) (2021)
- [CLAWSAT: Towards Both Robust and Accurate Code Models](https://mlsanity.com/paper/2211.11711/) (2022)
- [JEMMA: An Extensible Java Dataset for ML4Code Applications](https://mlsanity.com/paper/2212.09132/) (2022)
- [Study of Distractors in Neural Models of Code](https://mlsanity.com/paper/2303.01739/) (2023)
- [Coarse-Tuning Models of Code with Reinforcement Learning Feedback](https://mlsanity.com/paper/2305.18341/) (2023)
- [Demystifying What Code Summarization Models Learned](https://mlsanity.com/paper/2303.02333/) (2023)

## Abstract (arXiv)

Neural program embedding can be helpful in analyzing large software, a task that is challenging for traditional logic-based program analyses due to their limited scalability. A key focus of recent machine-learning advances in this area is on modeling program semantics instead of just syntax. Unfortunately evaluating such advances is not obvious, as program semantics does not lend itself to straightforward metrics. In this paper, we introduce a benchmarking framework called COSET for standardizing the evaluation of neural program embeddings. COSET consists of a diverse dataset of programs in source-code format, labeled by human experts according to a number of program properties of interest. A point of novelty is a suite of program transformations included in COSET. These transformations when applied to the base dataset can simulate natural changes to program code due to optimization and refactoring and can serve as a "debugging" tool for classification mistakes. We conducted a pilot study on four prominent models: TreeLSTM, gated graph neural network (GGNN), AST-Path neural network (APNN), and DYPRO. We found that COSET is useful in identifying the strengths and limitations of each model and in pinpointing specific syntactic and semantic characteristics of programs that pose challenges.