# Unknown Unknowns: Model Misspecification in Machine Learning for Physics

arXiv: https://arxiv.org/abs/2608.13633 · HTML: https://mlsanity.com/paper/2608.13633/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 67 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [The frontier of simulation-based inference](https://mlsanity.com/paper/1911.01429/) (2019)
- [Lorentz Group Equivariant Neural Network for Particle Physics](https://mlsanity.com/paper/2006.04780/) (2020)
- [Approximating Likelihood Ratios with Calibrated Discriminative Classifiers](https://mlsanity.com/paper/1506.02169/) (2015)
- [A Living Review of Machine Learning for Particle Physics](https://mlsanity.com/paper/2102.02770/) (2021)
- [Learning to Pivot with Adversarial Networks](https://mlsanity.com/paper/1611.01046/) (2016)
- [Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models](https://mlsanity.com/paper/2401.13537/) (2024)
- [Investigating the Impact of Model Misspecification in Neural Simulation-based Inference](https://mlsanity.com/paper/2209.01845/) (2022)
- [Classification without labels: Learning from mixed samples in high energy physics](https://mlsanity.com/paper/1708.02949/) (2017)
- [Parameterized Machine Learning for High-Energy Physics](https://mlsanity.com/paper/1601.07913/) (2016)
- [Evaluating generative models in high energy physics](https://mlsanity.com/paper/2211.10295/) (2022)
- [A Lorentz-Equivariant Transformer for All of the LHC](https://mlsanity.com/paper/2411.00446/) (2024)
- [Addressing Misspecification in Simulation-based Inference through Data-driven Calibration](https://mlsanity.com/paper/2405.08719/) (2024)
- [PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics](https://mlsanity.com/paper/2211.00454/) (2022)
- [Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks](https://mlsanity.com/paper/2010.09206/) (2020)
- [Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models](https://mlsanity.com/paper/2403.07066/) (2024)
- [An unfolding method based on conditional Invertible Neural Networks (cINN) using iterative training](https://mlsanity.com/paper/2212.08674/) (2022)
- [The Landscape of Unfolding with Machine Learning](https://mlsanity.com/paper/2404.18807/) (2024)
- [INFERNO: Inference-Aware Neural Optimisation](https://mlsanity.com/paper/1806.04743/) (2018)
- [A Probabilistic Framework for LLM-Based Model Discovery](https://mlsanity.com/paper/2602.18266/) (2026)
- [Reweighting with Boosted Decision Trees](https://mlsanity.com/paper/1608.05806/) (2016)
- [neos: End-to-End-Optimised Summary Statistics for High Energy Physics](https://mlsanity.com/paper/2203.05570/) (2022)
- [Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Review](https://mlsanity.com/paper/2007.09121/) (2020)
- [Flow Away your Differences: Conditional Normalizing Flows as an Improvement to Reweighting](https://mlsanity.com/paper/2304.14963/) (2023)
- [Transport away your problems: Calibrating stochastic simulations with optimal transport](https://mlsanity.com/paper/2107.08648/) (2021)
- [One flow to correct them all: improving simulations in high-energy physics with a single normalising flow and a switch](https://mlsanity.com/paper/2403.18582/) (2024)
- [Tests for model misspecification in simulation-based inference: from local distortions to global model checks](https://mlsanity.com/paper/2412.15100/) (2024)

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

- [VERaiPHY -- Validation & Evaluation for Robust AI in PHYsics](https://mlsanity.com/paper/2608.17724/) (2026)

## Abstract (arXiv)

Machine learning is now a central tool for solving inverse problems in particle physics and astronomy. Models are trained on simulation and deployed on real data, raising the question not just of whether they fit, but of whether they are wrong in ways we did not anticipate: the unknown unknowns. This challenge of model misspecification is not unique to machine learning. In physics, misspecification is sometimes exactly what we want to find: new discoveries appear as failures of existing models. At other times, we want such effects absorbed into the analysis without biasing the measurement. A robust analysis is one that absorbs the misspecifications we are not interested in, while preserving sensitivity to the ones we are. Machine learning can both amplify misspecification and provide new tools to address it. We discuss the challenges of model misspecification, diagnostics for detecting it, and strategies for mitigation. No single diagnostic can confirm that a model is correctly specified: detection and mitigation are two halves of an iterative loop, in which a battery of complementary diagnostics is applied, the model is updated, and the process repeated. Robustness against unknown unknowns is ultimately less about any single technique than about a disposition: a willingness to suspect one's own model, and to design analyses that can survive being wrong in ways one did not anticipate.