Reproduce “An AI-Powered Multiverse Analysis of Empirical Finance Research: Evidence from Reused Natural Experiments” 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
Ruijiang Gao, Steven Chong Xiao
Gao and Xiao use AI agents to reproduce and test empirical finance papers across defensible analysis choices. They apply a checked workflow to 324 papers using 13 natural experiments. For 306 directional claims, only 25% of 59,106 specifications preserve the published sign and meet the study’s significance cutoff. This measures dependence on analysis choices, not whether unsupported claims are false.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.