# Aligning AI-driven discovery with human intuition

arXiv: https://arxiv.org/abs/2410.07397 · HTML: https://mlsanity.com/paper/2410.07397/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 52 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 13 of 13)

- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Discovering Symbolic Models from Deep Learning with Inductive Biases](https://mlsanity.com/paper/2006.11287/) (2020)
- [Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics](https://mlsanity.com/paper/1707.09571/) (2017)
- [Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations](https://mlsanity.com/paper/1711.10566/) (2017)
- [Machine Learning of Linear Differential Equations using Gaussian Processes](https://mlsanity.com/paper/1701.02440/) (2017)
- [Flexible Neural Representation for Physics Prediction](https://mlsanity.com/paper/1806.08047/) (2018)
- [Constructions in combinatorics via neural networks](https://mlsanity.com/paper/2104.14516/) (2021)
- [Numerical Aspects for Approximating Governing Equations Using Data](https://mlsanity.com/paper/1809.09170/) (2018)
- [Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systems](https://mlsanity.com/paper/2305.02251/) (2023)
- [Structure-preserving Method for Reconstructing Unknown Hamiltonian Systems from Trajectory Data](https://mlsanity.com/paper/1905.10396/) (2019)
- [Exactly Sparse Gaussian Variational Inference with Application to Derivative-Free Batch Nonlinear State Estimation](https://mlsanity.com/paper/1911.08333/) (2019)
- [Deep Neural Networks to Recover Unknown Physical Parameters from Oscillating Time Series](https://mlsanity.com/paper/2101.03850/) (2021)
- [Koopman Linearization for Data-Driven Batch State Estimation of Control-Affine Systems](https://mlsanity.com/paper/2109.07000/) (2021)

## Built on by (most cited first, 1 of 1)

- [LyTimeT: Towards Robust and Interpretable State-Variable Discovery](https://mlsanity.com/paper/2510.19716/) (2025)

## Abstract (arXiv)

As data-driven modeling of physical dynamical systems becomes more prevalent, a new challenge is emerging: making these models more compatible and aligned with existing human knowledge. AI-driven scientific modeling processes typically begin with identifying hidden state variables, then deriving governing equations, followed by predicting and analyzing future behaviors. The critical initial step of identification of an appropriate set of state variables remains challenging for two reasons. First, finding a compact set of meaningfully predictive variables is mathematically difficult and under-defined. A second reason is that variables found often lack physical significance, and are therefore difficult for human scientists to interpret. We propose a new general principle for distilling representations that are naturally more aligned with human intuition, without relying on prior physical knowledge. We demonstrate our approach on a number of experimental and simulated system where the variables generated by the AI closely resemble those chosen independently by human scientists. We suggest that this principle can help make human-AI collaboration more fruitful, as well as shed light on how humans make scientific modeling choices.