# AI verification proposal

A proposal built with the Proposal Explorer of the AI Verification Tech Map (https://trustbutveri.fyi/), from its records of 2026-10-08. Interactive version: https://trustbutveri.fyi/explorer/?mechanisms=M-0007,M-0001&implementations=M-0001:I-0002

How to read it: a claim is something one party wants to verify about another's AI hardware or software. A mechanism is a general technique for verifying claims; it is "aimed at" a claim when that is its direct purpose, and "supporting" when it contributes without being aimed at it. A claim is addressed when a mechanism in the proposal is aimed at it and is not excluded by the filters; addressed does not mean verified, so check that mechanism's readiness and open flaws. Readiness levels R0 to R4 describe one record's public evidence for its assessed use and are never combined. Definitions: https://trustbutveri.fyi/about/methodology/ (roles, properties and flaws) and https://trustbutveri.fyi/about/readiness/ (readiness levels).

## Filters

Filters apply to mechanisms only and describe the setting the proposal is for.

None set. Every mechanism on the map was available.

## Overview

One row per mechanism, read from its record. Open flaws: critical / significant / minor. The last three columns are the editors' reading of what the verifier sees.

| Mechanism | Readiness | Prover | Attack testing | Hardware | Open flaws | Weights | Inputs and outputs | Training data |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Proofs of useful work for capacity accounting | R1 | Adversarial | Analysis | None | 0 / 3 / 0 | depends | depends | not involved |
| Sampled inference recomputation / DiFR (Divergence From Reference) | R2 | Adversarial | Analysis | None | 0 / 2 / 1 | unspecified | unspecified | unspecified |

## Claims

No claims chosen.

## Mechanisms

### Proofs of useful work for capacity accounting

Cryptographic evidence that a given amount of matrix-multiplication work was completed, proposed as one input to accounting for spare capacity on declared hardware. ([Proofs of useful work for capacity accounting](https://trustbutveri.fyi/mechanisms/proofs-of-useful-work/))

- Assessment: mechanism family.
- Readiness: R1 Proposed, assessed for bounding the spare capacity of declared hardware that could run training.
- Claims in this proposal: none of them.
- Threat model: adversarial prover. Hardware: none. Prover cooperation: required. Attack testing: analysis. Category: Cryptographic & computational.
- What the verifier sees: model weights depends; inputs and outputs depends; training data not involved. Checking a sampled tile of a matrix multiplication reveals that tile, which may hold model or input data; the authors suggest a zero-knowledge proof when the matrices must stay private.

### Sampled inference recomputation

DiFR checks that an inference provider ran its declared model by comparing output tokens or activations with a trusted re-run using the same random seed. ([Sampled inference recomputation](https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/))

- Assessment: selected implementation [DiFR (Divergence From Reference)](https://trustbutveri.fyi/implementations/difr/).
- Readiness: R2 Demonstrated, assessed for checking that outputs match the declared model, precision and sampling settings.
- Claims in this proposal: none of them.
- Threat model: adversarial prover. Hardware: none. Prover cooperation: required. Attack testing: analysis. Category: Cryptographic & computational.
- What the verifier sees: model weights unspecified; inputs and outputs unspecified; training data unspecified. This Explorer has no asset-specific exposure assessment for this implementation. Check its source and deployment assumptions.


## Properties

**Built for an adversarial prover**

- Proofs of useful work for capacity accounting
- Sampled inference recomputation

**No new hardware needed**

- Proofs of useful work for capacity accounting
- Sampled inference recomputation


## Attack testing

Published attempts to break a system, including those that found failures. Testing history does not establish that open flaws are resolved.

**Testing history**

- Proofs of useful work for capacity accounting: Analysis
- Sampled inference recomputation / DiFR (Divergence From Reference): Analysis


## Limits

**Open significant flaws**

- Proves that work was done, not that no capacity remains (theoretical argument, in Proofs of useful work for capacity accounting; https://trustbutveri.fyi/mechanisms/proofs-of-useful-work/#flaw-1) [1]. Proof-of-work accounting bounds unmonitored compute only relative to an estimate of what the actor has. Attestable states that the verifier "needs a credible estimate of the compute available" to the actor, and that a proof "cannot discover a datacenter that was never declared".

  Related mechanism: Chip registries and manufacturing records (R1, not in the proposal). A registry of chips is one basis for the estimate of available compute that the flaw's source says the verifier needs.

  Related mechanism: Remote detection of data centres (R1, not in the proposal). Looks for data centres that were never declared, which a proof cannot discover.
- Security rests on new hardness assumptions (open question, in Proofs of useful work for capacity accounting; https://trustbutveri.fyi/mechanisms/proofs-of-useful-work/#flaw-2) [3][4]. Komargodski and Weinstein base security on hardness assumptions about batches of low-rank random linear equations, and list PoUW "from more standard or well-studied assumptions" as an open problem. Pearl's floating-point variant introduces a further "quantized-subspace hardness" assumption.
- Known shortcuts let a miner claim somewhat more work than it did (theoretical argument, in Proofs of useful work for capacity accounting; https://trustbutveri.fyi/mechanisms/proofs-of-useful-work/#flaw-3) [4]. Pearl's specification lists known mining speedups: crafted inputs, precision shortcuts, seed grinding, work reuse, and faster kernels or hardware. A policy check caps the summands a miner may skip at one-sixteenth of those in a tile. For capacity bounding, any gap between work proven and work possible leaves spare capacity.
- Statistical tolerance leaves a covert channel (demonstrated attack, in DiFR (Divergence From Reference); https://trustbutveri.fyi/implementations/difr/#flaw-1) [7][12][14]. Statistical schemes can put an upper bound on an adversary's covert bandwidth, but cannot close it. In the companion exfiltration study, the detector cut exfiltratable information to under 0.5% under benign prompt traffic. It did not cut it to zero. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study attacked that detector, which uses the same Gumbel-margin statistic. An adversary who controls the prompts roughly doubled the bits leaked per token. Across six models, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target DiFR's check that outputs match the declared configuration.
- Speculative decoding and multi-model sampling not evaluated (open question, in DiFR (Divergence From Reference); https://trustbutveri.fyi/implementations/difr/#flaw-3) [6]. The algorithms and experiments cover sampling from a single LLM. Speculative decoding was not evaluated. The authors sketch an extension to one speculative-decoding algorithm, without experiments. They note that other variants would need modified verification and extra metadata.

**Family finding context**

- Context for DiFR (Divergence From Reference); applicability depends on the finding's scope. Tolerance for numerical noise leaves a covert channel (demonstrated attack, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-1) [7][12][14]. Schemes that accept approximate matches can put an upper bound on an adversary's covert bandwidth, but they cannot close the channel. The weight-exfiltration detector cut exfiltratable information to under 0.5%, not to zero, on a 30-billion-parameter mixture-of-experts model under benign prompt traffic. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token. Across six models, that cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target the check that outputs match the declared model.

  Related mechanism: Deterministic and bit-exact inference (R3, not in the proposal). Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration.
- Context for DiFR (Divergence From Reference); applicability depends on the finding's scope. Only recorded traffic is checked (theoretical argument, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-2) [7][15]. Recomputation checks that recorded, declared workloads are correct. It cannot show that the record is complete. The published schemes do not cover hidden workloads run on the same compute, or substituted work. Rinberg et al. say their exfiltration-detection scheme cannot stand alone.

  Related mechanism: Network taps and certifiers (R1, not in the proposal). Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips.
- Context for DiFR (Divergence From Reference); applicability depends on the finding's scope. Some inference optimizations are not covered (theoretical argument, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-3) [6][16]. TOPLOC's authors state that it cannot detect speculative decoding in which a cheaper model does the decoding. They did not test whether it distinguishes types of key-value (KV) cache compression. DiFR was evaluated only on sampling from a single model. Its authors sketch an extension to one speculative-decoding algorithm but do not test it.
- Context for DiFR (Divergence From Reference); applicability depends on the finding's scope. Mixed hardware widens the honest baseline (open question, in Sampled inference recomputation; https://trustbutveri.fyi/mechanisms/sampled-inference-recomputation/#flaw-4) [6]. When honest reference runs span different GPU types, the spread of benign scores grows. In DiFR's tests on Qwen3-30B-A3B, pooling A100 and H200 runs left Token-DiFR unable to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy separated them. Matched provider and verifier environments, or pooling that weights rare large deviations, restored detection.

**Open minor flaws**

- Mixed hardware widens the honest baseline (open question, in DiFR (Divergence From Reference); https://trustbutveri.fyi/implementations/difr/#flaw-2) [6]. For Qwen3-30B-A3B, pooling honest runs across A100 and H200 GPUs and parallelism setups broadened the honest score distribution. Token-DiFR then failed to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy did. The authors report that matched provider and verifier environments, or pooling that weights rare large deviations, restore detection.

**Not yet demonstrated**

- Proofs of useful work for capacity accounting: R1 Proposed, assessed for bounding the spare capacity of declared hardware that could run training


## Possible additions

Mechanisms on the map, not in the proposal, that the records connect to an unaddressed or partly addressed claim, an open flaw or a dependency. Pointers, not recommendations: each brings its own readiness level and flaws, and none is claimed to close a flaw.

- **Chip registries and manufacturing records** (R1 Proposed, assessed for a checkable record of which chips were made and who declared owning them)
  - Bears on the open significant flaw "Proves that work was done, not that no capacity remains" in Proofs of useful work for capacity accounting. A registry of chips is one basis for the estimate of available compute that the flaw's source says the verifier needs.
- **Remote detection of data centres** (R1 Proposed, assessed for finding undeclared data centres above an agreed compute threshold)
  - Bears on the open significant flaw "Proves that work was done, not that no capacity remains" in Proofs of useful work for capacity accounting. Looks for data centres that were never declared, which a proof cannot discover.


## Dependencies

**Blockers**

- Proofs of useful work for capacity accounting: Bounding spare capacity needs a credible estimate of the compute available to the actor, including third-party access. (capacity bounds) [1]
- Proofs of useful work for capacity accounting: Proofs of work cannot find facilities that were never declared. (coverage & hidden compute) [1]
- Proofs of useful work for capacity accounting: As of September 2026 no implementation, demonstration or independent evaluation of proofs of work for capacity bounding has been published. (adversarial validation)
- Sampled inference recomputation: The verifier needs the model weights, so outsiders cannot use the method to verify providers of closed-weights models. (privacy & leakage) [6]
- Sampled inference recomputation: The verifier must know and match the provider's sampling procedure, and in one prototype a sampling mismatch in a newer vLLM version produced large spurious logit differences. (performance & compatibility) [6][9]
- Sampled inference recomputation: No independent red-team of DiFR's consistency check has been published, Amodo rates recomputation red-teaming 'not started', and the one independent attack study targets an exfiltration detector built on the same statistic. (adversarial validation) [11][12]


## What the verifier sees

- Model weights: shown by none; depends on the design for Proofs of useful work for capacity accounting; hidden by none; not involved in none; unspecified for Sampled inference recomputation.
- Inputs and outputs: shown by none; depends on the design for Proofs of useful work for capacity accounting; hidden by none; not involved in none; unspecified for Sampled inference recomputation.
- Training data: shown by none; depends on the design for none; hidden by none; not involved in Proofs of useful work for capacity accounting; unspecified for Sampled inference recomputation.

## Implementations

- Proofs of useful work for capacity accounting: [Pearl proof-of-useful-work blockchain](https://trustbutveri.fyi/implementations/pearl-proof-of-useful-work/) (R3, open-source project)
- Sampled inference recomputation: [AI 2040 inference-only verification stack](https://trustbutveri.fyi/implementations/ai-2040-inference-only-verification-plan/) (R1, proposed architecture); [DiFR (Divergence From Reference)](https://trustbutveri.fyi/implementations/difr/) (R2, research prototype); [Low-trust AI compute verification system overview](https://trustbutveri.fyi/implementations/low-trust-compute-verification-system-overview/) (R1, proposed architecture); [SASH confidential network logger](https://trustbutveri.fyi/implementations/sash-confidential-network-logger/) (R1, research prototype); [TOPLOC](https://trustbutveri.fyi/implementations/toploc/) (R3, open-source project)

## Sources

1. Pacing AI Requires Proof, Attestable (2026). https://attestable.com/blog/pacing-ai-requires-proof
2. Mechanisms to Verify International Agreements About AI Development, A. Scher & L. Thiergart (2025). https://arxiv.org/abs/2506.15867
3. Proofs of Useful Work from Arbitrary Matrix Multiplication, I. Komargodski & O. Weinstein (2025). https://arxiv.org/abs/2504.09971
4. Pearl Floating Point Scheme Specification, Pearl Research Team (2026). https://pearlresearch.ai/Pearl_Whitepaper.pdf
5. pearl: Monorepo for the Pearl network, Pearl Research Labs (2026). https://github.com/pearl-research-labs/pearl
6. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). https://arxiv.org/abs/2511.20621
7. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). https://arxiv.org/abs/2511.02620
8. adamkarvonen/difr (GitHub repository), A. Karvonen (2025). https://github.com/adamkarvonen/difr
9. Scaling Recomputation Inference Verification, Amodo Design (2026). https://amododesign.com/notes/2026-09-02-scaling-recomputation-inference-verification/
10. Amodo-Design/Inference-Recomputation-Prototype (GitHub repository), Amodo Design (2026). https://github.com/Amodo-Design/Inference-Recomputation-Prototype
11. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). https://amododesign.com/ai-verification/plan-a-sitrep/
12. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). https://arxiv.org/abs/2608.23375
13. An Inference Verification Prototype — Stage 1, Amodo Design (2026). https://amododesign.com/notes/2026-06-29-inference-verification-prototype/
14. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). https://arxiv.org/abs/2606.00279
15. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). https://amododesign.com/notes/2026-06-23-verification-algorithms/
16. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). https://proceedings.mlr.press/v267/ong25a.html