Skip to content

TopoPrimer

Home / Concepts / TopoPrimer

TopoPrimer

Auto-generated stub. Edit this file to add more details.

A forecasting framework that injects the global topological structure of series populations as explicit input features using persistent homology and spectral sheaf coordinates.

Why It Matters

The paper introduces a novel, model-agnostic method to inject population-level topological features via persistent homology and spectral sheaf coordinates, which provides a distinct inductive bias for time-series foundation models.

Evidence

We introduce TopoPrimer, a framework that makes the global topological structure of the series population an explicit input to any forecasting model.

Metadata & Links