ReproBridge: Building Reproducibility into ML Research Artifacts
arXiv cs.AI · 6 Nov 2026, 04:45 AEST
ReproBridge aims to enhance the reproducibility of machine learning experiments by standardizing artifact design. The introduction of refined artifacts significantly improves reproduction success rates and reduces API spending.
Key facts
- Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts.
- We define a standardized artifact design comprising a refined codebase, environment setup, experiment launchers, and a reproduction guide, and introduce ReproBridge.
- Across four evaluated models, refined artifacts raise mean reproduction success from 76.4% to 92.6% and reduce downstream API spending by 19.7% on average.
- Removing any component reduces success in the ablation study, with the largest losses from code and environment removal.
Read aloud
ReproBridge aims to enhance the reproducibility of machine learning experiments by standardizing artifact design. The introduction of refined artifacts significantly improves reproduction success rates and reduces A P I spending. Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. We define a standardized artifact design comprising a refined codebase, environment setup, experiment launchers, and a reproduction guide, and introduce ReproBridge. Across four evaluated models, refined artifacts raise mean reproduction success from seventy six point four percent to ninety two point six percent and reduce downstream A P I spending by nineteen point seven percent on average. Removing any component reduces success in the ablation study, with the largest losses from code and environment removal.
Sources in this cluster
- ReproBridge: Building Reproducibility into ML Research Artifacts
arXiv cs.AI · 6 Nov 2026, 04:45 AEST