Skip to content

ReproScreener

ReproScreener is the research software associated with a peer-reviewed 2024 study of keyword and GPT-4 screening for reproducibility-related signals in paper abstracts 1.

Warning

Later local-model, full-manuscript, and repository experiments are unpublished prototypes rather than validated extensions of the 2024 study. Read Corrections and research scope before interpreting those files.

  1. Bhaskar, A. and Stodden, V. 2024. Reproscreener: Leveraging LLMs for Assessing Computational Reproducibility of Machine Learning Pipelines. Proceedings of the 2nd ACM Conference on Reproducibility and Replicability (New York, NY, USA, Jul. 2024), 101--109. ↩