# Measuring the Completeness of Theories

arXiv: https://arxiv.org/abs/1910.07022 · HTML: https://mlsanity.com/paper/1910.07022/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [Position: Use Sparse Autoencoders to Discover Unknowns](https://mlsanity.com/paper/2506.23845/) (2025)
- [Capturing the Complexity of Human Strategic Decision-Making with Machine Learning](https://mlsanity.com/paper/2408.07865/) (2024)
- [Improving Human Sequential Decision-Making with Reinforcement Learning](https://mlsanity.com/paper/2108.08454/) (2021)
- [Causal Inference on Outcomes Learned from Text](https://mlsanity.com/paper/2503.00725/) (2025)
- [Explaining and Improving Information Complementarities in Multi-Agent Decision-making](https://mlsanity.com/paper/2502.06152/) (2025)
- [How to Evaluate Behavioral Models](https://mlsanity.com/paper/2306.04778/) (2023)

## Abstract (arXiv)

We use machine learning to provide a tractable measure of the amount of predictable variation in the data that a theory captures, which we call its "completeness." We apply this measure to three problems: assigning certain equivalents to lotteries, initial play in games, and human generation of random sequences. We discover considerable variation in the completeness of existing models, which sheds light on whether to focus on developing better models with the same features or instead to look for new features that will improve predictions. We also illustrate how and why completeness varies with the experiments considered, which highlights the role played in choosing which experiments to run.