Reproduce “Exploring utilization of generative AI for research and education in data-driven materials science” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Takahiro Misawa, Ai Koizumi, Ryo Tamura, Kazuyoshi Yoshimi
The authors describe three uses of generative AI explored by 30 participants at AIMHack2024 in July 2024: asking AI for ImageJ instructions, supplying documentation to a PHYSBO tutor, and turning Python code into a Windows interface. They report watershed separation of touching circles and 0.9742 accuracy on MNIST, but no baseline or timed comparison; human validation remains necessary.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.