Data-driven models are increasingly adopted in critical scientific fields like weather forecasting and fluid dynamics. These methods can fail on out-of-distribution (OOD) data, but detecting such failures in regression tasks is an open challenge. We propose a new OOD detection method based on estimating joint likelihoods using a score-based diffusion model. This approach considers not just the input but also the regression model's prediction, providing a task-aware reliability score. Across numerous scientific datasets, including PDE datasets, satellite imagery and brain tumor segmentation, we show that this likelihood strongly correlates with prediction error. Our work provides a foundational step towards building a verifiable 'certificate of trust', thereby offering a practical tool for assessing the trustworthiness of AI-based scientific predictions. Our code is publicly available at https://github.com/bogdanraonic3/OOD_Detection_ScientificML
@article{arxiv.2509.25080,
title = {Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI},
author = {Bogdan Raonić and Siddhartha Mishra and Samuel Lanthaler},
journal= {arXiv preprint arXiv:2509.25080},
year = {2026}
}