mlsanityData to 7 Oct 2026

Unknown Unknowns: Model Misspecification in Machine Learning for Physics

arXiv 2608.13633 ↗First posted 13 Aug 2026physics.data-an astro-ph.CO astro-ph.GAcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 26 of its 67 references that are in the map. First posted on arXiv 13 Aug 2026.

Builds on

26 of 67 references.

References · 26

  1. 2019The frontier of simulation-based inferencecited by 490
  2. 2020Lorentz Group Equivariant Neural Network for Particle Physicscited by 120
  3. 2015Approximating Likelihood Ratios with Calibrated Discriminative Classifierscited by 87
  4. 2021A Living Review of Machine Learning for Particle Physicscited by 77
  5. 2016Learning to Pivot with Adversarial Networkscited by 55
  6. 2022Investigating the Impact of Model Misspecification in Neural Simulation-based Inferencecited by 44
  7. 2024Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Modelscited by 44
  8. 2017Classification without labels: Learning from mixed samples in high energy physicscited by 42
  9. 2016Parameterized Machine Learning for High-Energy Physicscited by 33
  10. 2022Evaluating generative models in high energy physicscited by 31
  11. 2024A Lorentz-Equivariant Transformer for All of the LHCcited by 27
  12. 2022PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physicscited by 26
14 more
  1. 2024Addressing Misspecification in Simulation-based Inference through Data-driven Calibrationcited by 26
  2. 2020Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networkscited by 22
  3. 2024Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Modelscited by 21
  4. 2022An unfolding method based on conditional Invertible Neural Networks (cINN) using iterative trainingcited by 20
  5. 2024The Landscape of Unfolding with Machine Learningcited by 20
  6. 2018INFERNO: Inference-Aware Neural Optimisationcited by 16
  7. 2016Reweighting with Boosted Decision Treescited by 10
  8. 2022neos: End-to-End-Optimised Summary Statistics for High Energy Physicscited by 10
  9. 2026A Probabilistic Framework for LLM-Based Model Discoverycited by 10
  10. 2020Dealing with Nuisance Parameters using Machine Learning in High Energy Physics: a Reviewcited by 9
  11. 2023Flow Away your Differences: Conditional Normalizing Flows as an Improvement to Reweightingcited by 6
  12. 2021Transport away your problems: Calibrating stochastic simulations with optimal transportcited by 5
  13. 2024One flow to correct them all: improving simulations in high-energy physics with a single normalising flow and a switchcited by 4
  14. 2024Tests for model misspecification in simulation-based inference: from local distortions to global model checkscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026VERaiPHY -- Validation & Evaluation for Robust AI in PHYsicscited by 0