Reproduce “A Multi-Asset Dataset and Tail-Risk Framework for DeFi Yield Trading Derivatives” 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

Huaiyu Jia, Jieshun You, Jingyu Liu, Yizhi Luo, Shuo Sun

The authors assemble an hourly, 24-month dataset of 340 Pendle markets and propose Tail-MSE, which penalizes forecasts that underestimate realized volatility more than forecasts that overestimate it. They test PT-entry strategies in a historical, zero-slippage backtest. Mamba’s reported tail-error score falls from 0.083 to 0.051 at α=3; Tail-MSE has the highest ROI in 181/340 markets, not universally.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.