Reproduce “Measuring What is Repeated and Novel in Earnings Disclosures Using Optimal Transport” 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
Yuntao Wu, Lynn Tao, Charles Martineau, Vincent Grégoire, Andreas Veneris
The authors examine how press-release and conference-call Q&A text relate to earnings announcement returns. They match semantically similar paragraphs using optimal transport, then separate shared from source-specific content. In the full comparison, both aligned and unmatched call scores are significant, while unmatched press-release content is not. These are predictive associations, not evidence of causal effects.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.