AI-Assisted Computational Reproducibility on the FABRIC Testbed
For researchers seeking to reproduce computational experiments, this work shows a practical approach to reduce reproduction effort, but the results are incremental and domain-specific.
The authors demonstrate that combining the FABRIC testbed with LLM-based coding assistants (LoomAI) can reduce the effort required to reproduce published experiments by roughly 4–6 times across three case studies, though the AI struggled with analysis stages lacking defined workflows.
Computational reproducibility remains difficult despite being central to scientific research. In this paper, we show how the international FABRIC testbed, combined with large language model (LLM) coding assistants through LoomAI, can simplify reproducing published experiments across multiple domains. We reproduced three case studies on FABRIC, covering BBR-family congestion-control evaluations, LAMMPS molecular dynamics scaling benchmarks on a CPU-only MPI cluster, and stress protein homeostasis genomics pipelines. Rather than focusing only on matching numerical outputs, we evaluate whether the reproduced experiments support the same scientific conclusions as the original studies. The AI assistant was effective in setting up the environment, adapting code, and debugging, but struggled with the analysis stages that lacked clearly defined workflows, which required human guidance to establish execution order and data dependencies. Across the case studies, the AI-assisted workflow reduced reproduction effort by roughly 4--6 times. We conclude with practical recommendations for improving AI-assisted reproducibility on research testbeds.