DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory

arXiv:2607.23614 · cs.CR, cs.AI, cs.LG, hep-th · Submitted 2026-07-26 · Read on arXiv

cs.CR, cs.AI, cs.LG, hep-th

Submitted: 2026-07-26

Updated: 2026-09-28

Comments: 17 pages, 2 figures, 9 tables. v2: added reference and note on concurrent related work. Code, benchmark, and all per-attempt records: https://github.com/xingyang-yu/QFTCert

Code: https://github.com/xingyang-yu/QFTCert

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verifier — 81× in this paper · explained in 2 episodes
• Consistency — 32× in this paper · explained in 3 episodes
• Benchmark — 24× in this paper · explained in 2 episodes
• Trace — 10× in this paper · explained in 2 episodes
• Verification — 7× in this paper · explained in 2 episodes
• Axioms — 4× in this paper · explained in 2 episodes
• Clustering — 3× in this paper · explained in 2 episodes
• Provenance — 3× in this paper · explained in 3 episodes
• Abstention — 2× in this paper · explained in 1 episode
• Iterative Refinement — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Longitudinal Data — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Symmetry Breaking — 1× in this paper · explained in 3 episodes

Sources

• Grading the Unspoken: Evaluating Tacit Reasoning in Quantum Field Theory and String Theory with LLMs
• Theoretical Physics Benchmark (TPBench) -- a Dataset and Study of AI Reasoning Capabilities in Theoretical Physics
• Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark
• LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
• Resolution of Erd\H{o}s Problem #728: a writeup of Aristotle's Lean proof
• Learning to Disprove: Formal Counterexample Generation with Large Language Models
• Electric-Magnetic Duality in Supersymmetric Non-Abelian Gauge Theories
• Lectures on supersymmetric gauge theories and electric-magnetic duality
• HepLean: Digitalising high energy physics
• Large Language Models Cannot Self-Correct Reasoning Yet
• Training Verifiers to Solve Math Word Problems
• Teaching Large Language Models to Self-Debug
• Self-Refine: Iterative Refinement with Self-Feedback
• Reflexion: Language Agents with Verbal Reinforcement Learning
• Let's Verify Step by Step
• Quiver Mutations, Seiberg Duality and Machine Learning
• Learning to Trace Seiberg Dualities
• Formalization of QFT
• Axioms for physical reasoning: codifying the Seiberg--Witten solution in Lean
• PhysProver: Advancing Automatic Theorem Proving for Physics

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs