P085 Inference verification for closed-weight models in production
Can inference be verified for closed-weight models on a lab's production stack?
Verifying inference for closed-weight models on a lab's own production serving stack, e.g. inside an attested enclave.
Status
Analyzed Design only: the AI 2040 and Amodo plan verifies production inference by tapping the prover's network and recomputing on a verifier-trusted server placed inside the prover's data centre, so closed weights never leave; the SITREP marks recomputation-server security 'Not on track'. Amodo asks labs to re-implement its open-weight demo on their own stacks with frontier models (not done); Karvonen et al. state DiFR cannot verify closed-weight providers (a design limit, not a test); Cankaya says proprietary-model verification would need third-party- or hardware-attested deployment (one sentence).
Whilst simpler than developing a whole SL5 cluster, the recomputation server needs to sit within the prover's data centre, possibly under their physical control.
Raised in: Cankaya (2026), All Hands on Deck to Build the Datacenter Lie Detector; Karvonen et al. (2025), DiFR: Inference Verification Despite Nondeterminism; Amodo (2026), AI 2040 Plan A — How You Can Help.
Sub-questions
| ID | Sub-question | What the sources report |
|---|---|---|
| P085.1 | Can statistical replay run inside an attested enclave for closed-weight models at a stated low overhead? | open |
| P085.2 | Does Token-DiFR separate an honest from a swapped frontier model on a lab's production stack? | open |
Possibly relevant work found by automated search
Found by AI agents searching for this problem's sub-questions, mostly by keyword and citation in the OpenAlex scholarly database and on the web; a second AI pass reviewed each one, and we spot-checked some by hand. They seemed reasonably related, as far as one can tell from outside each paper's field. Some come from neighbouring fields, such as arms control and financial audit, and bear on the problem by analogy. Not reviewed against the status above; a paper listed here does not change that status. 928 of 1052 quotes checked word for word against the paper's text.
For P085.1: Can statistical replay run inside an attested enclave for closed-weight models at a stated low overhead?
Data
- problems.csv — one row per problem
- problem_status.csv — status, scope and evidence per problem
- problem_sources.csv — the posed-by quote and other documents per problem
- leaves.csv — all sub-questions, including those without a checkable form
- leaf_sources.csv — every source row behind each sub-question