tsi - Trustworthy Scientific Inference

The TSI (Trustworthy Scientific Inference) package is an open-source Python implementation of the Frequentist-Bayes (FreB) protocol, developed alongside James Carzon, Luca Masserano, Alex Shen, and Antonio Carlos Herling Ribeiro Junior as part of collaborative research at CMU’s STAMPS Research Center. This package addresses a critical challenge in modern scientific computing: while generative AI models excel at solving inverse problems across scientific disciplines, they often produce biased or overconfident regions of uncertainty.

The open-source repository can be found here: GitHub