# Pessimistic Meta-Induction and Its Limits: Lessons from Frequentist Statistics and Machine Learning Theory

arXiv: https://arxiv.org/abs/2608.17213 · HTML: https://mlsanity.com/paper/2608.17213/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 28 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 2 of 2)

- [On Learning Causal Structures from Non-Experimental Data without Any Faithfulness Assumption](https://mlsanity.com/paper/1802.07051/) (2018)
- [Convergence to the Truth](https://mlsanity.com/paper/2410.11399/) (2024)

## Abstract (arXiv)

This paper challenges the pessimistic meta-inductive argument against scientific realism by undermining its inductive step rather than its historical premise. Although related challenges already exist, I develop a new one. Drawing on a general epistemology of scientific inference developed in frequentist statistics, machine learning, and formal epistemology, I evaluate induction in terms of convergence to the truth. I argue that ordinary enumerative induction can achieve everywhere convergence, whereas meta-induction fails even to achieve almost everywhere convergence. Indeed, in the problem context where meta-induction arises, the failure is deeper: no inference method whatsoever achieves almost everywhere convergence.