mlsanityData to 7 Oct 2026

Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough

arXiv 2607.10039 ↗First posted 10 Jul 2026physics.data-an cs.LG hep-phcited by 1

Not on the map. Why?

Abstract (arXiv)

Machine learning (ML) has become integral to fundamental physics, accelerating statistical workflows from data acquisition through inference and hypothesis testing. As ML systems grow increasingly autonomous, ensuring their reliability for discovery claims becomes critical. This review synthesizes the VERaiPHY (Validation & Evaluation for Robust AI in PHYsics) initiative's frameworks for rigorous ML assessment across particle physics, astrophysics, and cosmology. We establish when verification is essential by contextualizing ML within the statistical discovery workflow. We emphasize fundamental limitations: inductive bias is unavoidable, sample complexity bounds learning, and experimental constraints limit discovery. We reflect on physicists' evolving role as both experimental designers and evaluators whose judgments encode scientific rigor into AI systems. Responsible integration requires understanding ML's transformative potential alongside its intrinsic boundaries.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 47 of its 117 references that are in the map. First posted on arXiv 10 Jul 2026.

Builds on

47 of 117 references.

References · 47

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2020Scaling Laws for Neural Language Modelscited by 6,411
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2023Let's Verify Step by Stepcited by 3,598
  7. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  8. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  9. 2016Group Equivariant Convolutional Networkscited by 1,154
  10. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  11. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  12. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
35 more
  1. 2019The frontier of simulation-based inferencecited by 490
  2. 2021Explaining Neural Scaling Lawscited by 353
  3. 2018Deep learning generalizes because the parameter-function map is biased towards simple functionscited by 180
  4. 2020A Theory of Usable Information Under Computational Constraintscited by 153
  5. 2021The Low-Rank Simplicity Bias in Deep Networkscited by 150
  6. 2018Fast inference of deep neural networks in FPGAs for particle physicscited by 132
  7. 2021Equivariant Contrastive Learningcited by 65
  8. 2023The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learningcited by 63
  9. 2024Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Modelscited by 44
  10. 2026From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligencecited by 39
  11. 2018Learning to Predict the Cosmological Structure Formationcited by 38
  12. 2024CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulationcited by 34
  13. 2022Evaluating generative models in high energy physicscited by 31
  14. 2026MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verificationcited by 28
  15. 2024Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Modelscited by 21
  16. 2026There Will Be a Scientific Theory of Deep Learningcited by 21
  17. 2024Finetuning Foundation Models for Joint Analysis Optimizationcited by 18
  18. 2018Fast cosmic web simulations with generative adversarial networkscited by 13
  19. 2024Probing the effects of broken symmetries in machine learningcited by 13
  20. 2025Foundation models for high-energy physicscited by 10
  21. 2022Particle-based Fast Jet Simulation at the LHC with Variational Autoencoderscited by 7
  22. 2024Multiple testing for signal-agnostic searches of new physics with machine learningcited by 7
  23. 2025Learning to Validate Generative Models: a Goodness-of-Fit Approachcited by 4
  24. 2026Agentic AI -- Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Datacited by 4
  25. 2024PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstructioncited by 3
  26. 2026Generalizable Equivariant Diffusion Models for Non-Abelian Lattice Gauge Theorycited by 3
  27. 2026Uncertainty in Physics and AI: Taxonomy, Quantification, and Validationcited by 3
  28. 2026Model-Agnostic Signal Discovery with Machine Learning: Bridging the Gap Between Theory and Practicecited by 3
  29. 2024MACK: Mismodeling Addressed with Contrastive Knowledgecited by 2
  30. 2024Learning Broken Symmetries with Approximate Invariancecited by 2
  31. 2025AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testingcited by 2
  32. 2026Generative Models and Statistical Validationcited by 2
  33. 2026Statistical Properties of Training & Generalizationcited by 2
  34. 2026Interpreting "Interpretability" and Explaining "Explainability" in Machine Learning in Physicscited by 2
  35. 2020Coffea -- Columnar Object Framework For Effective Analysiscited by 1

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