Research · curated 26 Aug 2026
Deterministic Frontier-Scale Language Model Inference with Signed Receipts.
First reported zenodo.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
Verifiable, tamper-evident AI inference receipts address a core trust problem for defenders who must confirm that a model output was genuinely produced by a claimed model rather than fabricated or altered.
A whitepaper by Aishwary Singh ("Deterministic Frontier-Scale Language Model Inference with Signed Receipts") describes a protocol that produces byte-identical outputs from frontier-scale LLM inference and binds each output to an offline-verifiable Ed25519-signed CBOR receipt, with a probabilistic spot-check verifier that re-executes samples and rejects on mismatch. The construction runs across NVIDIA H100 and AMD MI300X hardware and is aimed at giving issuer-independent fabrication soundness for AI inference at production cost. Reference implementation is available at github.com/KuroKernel/ocx-protocol.