SciCoQA: Quality Assurance for Scientific Paper--Code Alignment

📰 ArXiv cs.AI

SciCoQA is a dataset for detecting discrepancies between scientific publications and their codebases

advanced Published 27 Mar 2026
Action Steps
  1. Construct a dataset from GitHub issues and reproducibility papers
  2. Propose a synthetic data generation method for constructing paper-code discrepancies
  3. Analyze paper-code discrepancies in detail and propose discrepancy types and categories
Who Needs to Know This

Data scientists and machine learning researchers on a team can benefit from SciCoQA to ensure faithful implementations of their research, while software engineers can use it to improve the quality of their codebases

Key Insight

💡 Ensuring faithful implementations of scientific research is crucial for reproducibility and reliability

Share This
🚀 Introducing SciCoQA: a dataset for detecting discrepancies between scientific papers and codebases! 💻

Key Takeaways

SciCoQA is a dataset for detecting discrepancies between scientific publications and their codebases

Full Article

Title: SciCoQA: Quality Assurance for Scientific Paper--Code Alignment

Abstract:
arXiv:2601.12910v2 Announce Type: replace-cross Abstract: We present SciCoQA, a dataset for detecting discrepancies between scientific publications and their codebases to ensure faithful implementations. We construct SciCoQA from GitHub issues and reproducibility papers, and to scale our dataset, we propose a synthetic data generation method for constructing paper-code discrepancies. We analyze the paper-code discrepancies in detail and propose discrepancy types and categories to better understa
Read full paper → ← Back to Reads