Establish semantic soundness of bounded-error normalization constraints
Establish whether every witness satisfying the finite-field approximation range permitted by the implemented LayerNorm and RMSNorm constraints yields the same output tokens as the intended canonical model.
References
The resulting finite-field relation admits an approximation range, and we have not proved that every witness inside that range yields the same output tokens.
— Seal, Then Sample: Sampled Layerwise Proofs for Verifiable LLM Inference from GPT-2 to 70B
(2609.27367 - Lim et al., 23 Sep 2026) in Section 2.1, “The object being verified”; discussed further in Section 8.2, “Approximate relations and model authenticity”