My background is in mathematics, philosophy, and machine learning. I am interested in model evaluations, reproducibility, and mechanistic interpretability.

See Mechanistic Research, where I am building methods, frameworks, and open-source tools for validating causal mechanisms across the sciences.

Background

Visiting Researcher — University of Edinburgh, School of Informatics (2026–present)

Independent Researcher — Mechanistic Research (2026–present)

Machine Learning Engineer — Eluve Inc (2024–2026)

Machine Learning Engineer — Swarm Labs (2023–2024)

M.S. Computer Science — University of Massachusetts Amherst (2020–2022)

B.S. Mathematics, Philosophy — University of Massachusetts Amherst (2016–2020)

Selected Publications

• Rajarshi Das, Ameya Godbole, Ankita Naik, Elliot Tower, Manzil Zaheer, Hannaneh Hajishirzi, Robin Jia, Andrew McCallum. Knowledge Base Question Answering by Case-based Reasoning over Subgraphs. ICML 2022. [Proceedings]

Preprints

• Elliot Tower. Mechanistic Validity: A Validity Theory, Research Methodology, and Evidence Standard for Mechanistic Claims. 2026. [Preprint]

• Elliot Tower. Mechanistic Views: An Atlas of Hidden Commitments and a Realism Criterion for Mechanistic Claims. 2026. [Preprint]

Current Research

1. Mechanistic Validity (Research Program)

Domain-general evidence standards for what warrants a mechanistic claim, how to resolve disputes about underlying mechanisms, and when a finding transfers between systems.

2. Reproducible Science (Software)

Open-source command-line tools for preregistration, results tracking, and citation verification. A plan is frozen before it runs, every number in a paper binds to the run that produced it, and every quoted passage resolves in its source.