The Discovery Engine is a general purpose automated system for scientific discovery, which combines machine learning with state-of-the-art ML interpretability to enable rapid and robust scientific insight across diverse datasets. In this paper, we benchmark the Discovery Engine against five recent peer-reviewed scientific publications applying machine learning across medicine, materials science, social science, and environmental science. In each case, the Discovery Engine matches or exceeds prior predictive performance while also generating deeper, more actionable insights through rich interpretability artefacts. These results demonstrate its potential as a new standard for automated, interpretable scientific modelling that enables complex knowledge discovery from data.
@article{arxiv.2507.00964,
title = {Benchmarking the Discovery Engine},
author = {Jack Foxabbott and Arush Tagade and Andrew Cusick and Robbie McCorkell and Leo McKee-Reid and Jugal Patel and Jamie Rumbelow and Jessica Rumbelow and Zohreh Shams},
journal= {arXiv preprint arXiv:2507.00964},
year = {2025}
}
Comments
16 pages, 8 figures, benchmarks Discovery Engine on five scientific datasets (medicine, materials science, climate, air quality, social science)