Large-Scale Anomaly Detection for Kotlin
We apply anomaly detection algorithms on all publicly avaliable Kotlin code to identify anomalous code fragments that can be of interest for the Kotlin compiler team.
Basically, we download all Kotlin code from GitHub, vectorize it, and feed it into an anomaly detection algorithm. We do the same for bytecode, where we can.We found a bunch of highly unconventional code snippets that are of interest for the Kotlin compiler team, and a few examples of suboptimal compiler behaviour.
The paper has been accepted at MSR 2020.
- Authorship Attribution of Source Code
- Automatic Classification of Error Types
- BSL Code Synthesizer
- Code Clone Detection
- Code Completion
- Code Representation
- Code Style Embeddings
- Coding Assistant
- Deep Bugs Detector
- Deep Code Completion
- Embeddings of Code Changes
- GitHub License Violations Study
- Java Context Helper
- Large-Scale Anomaly Detection for Kotlin
- NL-to-Code Synthesis
- Similar Repositories on GitHub
- The Dynamics of Topics in Code