data and code for CoMig
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This repository contains the code and dataset used for code-migration research. ALL these research questions use the same pipelie. ## Folder Overview ### CoMig-agents/ This folder contains the multi-agent migration pipeline implementation. - It includes the core agents for reading/analyzing code, planning migration steps, searching context, generating diffs, and verifying outputs. - It also contains evaluation and orchestration scripts that run the end-to-end migration workflow. In short, `CoMig-agents/` is the **engine** of the migration system. ### CoMig-data/ This folder contains migration benchmark samples and diff artifacts. - `*_a.py`: source-side version of a sample (after migration). - `*_b.py`: target-side version of a sample (before migration). - `*.diff`: textual patch showing changes between versions. In short, `CoMig-data/` is the **dataset** used for training/evaluation and case studies.
Fields of Study & Subjects
Software Engineering Research
Software Engineering Techniques and Practices
Model-Driven Software Engineering Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 27 March 2026
- Language
- EN