Stack-V-2
Emerging4papers using it
2024first seen
The 'Stack-V-2' dataset contains 25,000 Fortran code snippets and is used to evaluate the quality of cross-language code translation from Fortran to C++ through metrics like CodeBLEU.
Papers using Stack-V-2 (4)
- Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training DatasetsWhen to Ponder: Adaptive Compute Allocation for Code Generation via Test-Time TrainingStarCoder 2 and The Stack v2: The Next GenerationEnhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation