Proposal Explorer

Add claims to see which ones the mechanisms address.

In production

• R3 Deterministic and bit-exact inference for reproducing open-model inference from receipts in Gensyn's information-market service

Built for an adversarial prover

Proofs of useful work for capacity accounting and Deterministic and bit-exact inference

No new hardware needed

Proofs of useful work for capacity accounting and Deterministic and bit-exact inference

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

• Proofs of useful work for capacity accounting: Analysis
• Deterministic and bit-exact inference: Analysis

Open significant flaws

4 flaws in 2 mechanisms

• Proves that work was done, not that no capacity remains in Proofs of useful work for capacity accounting

  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". ¹

  Theoretical argument · Significant · Open. On the record

  Related mechanism R1 Chip registries and manufacturing records: A registry of chips is one basis for the estimate of available compute that the flaw's source says the verifier needs. A pointer, not evidence that this flaw is mitigated. Add

  Related mechanism R1 Remote detection of data centres: Looks for data centres that were never declared, which a proof cannot discover. A pointer, not evidence that this flaw is mitigated. Add

• Security rests on new hardness assumptions in Proofs of useful work for capacity accounting

  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. ^{3 4}

  Open question · Significant · Open. On the record

• Known shortcuts let a miner claim somewhat more work than it did in Proofs of useful work for capacity accounting

  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. ⁴

  Theoretical argument · Significant · Open. On the record

• Cross-hardware replay relies on reverse-engineered, closed behaviour in Deterministic and bit-exact inference

  Emulating one GPU's rounding on another requires reverse-engineering tensor-core arithmetic and modelling proprietary kernel choices. Hawkeye covers a subset of NVIDIA architectures and states that attention and other higher-level operations need further reverse engineering. For the bit-exact emulator, a proprietary Hopper kernel family is an open edge case. ^{6 8}

  Open question · Significant · Open. On the record

Open minor flaws

1 mechanism with minor findings

• Some kernels remain genuinely nondeterministic in Deterministic and bit-exact inference

  The bit-exact work separates kernels that are deterministic but not batch-invariant from truly nondeterministic ones that use atomic functions. Some integer de-quantization kernels use atomic additions and remain nondeterministic, so exact replay needs backends that avoid them. ⁶

  Open question · Minor · Open. On the record

Not yet demonstrated

R1 Proofs of useful work for capacity accounting

Mechanisms on the map that are not in the proposal. Pointers, not recommendations. ?

• R1 Chip registries and manufacturing records Add
  • 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.
• R1 Remote detection of data centres Add
  • 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.

Blockers

7 blockers recorded

• 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 work cannot find facilities that were never declared. Coverage & hidden compute ¹
  • As of September 2026 no implementation, demonstration or independent evaluation of proofs of work for capacity bounding has been published. Adversarial validation
• Deterministic and bit-exact inference
  • Batch-invariant kernels cost throughput: in Thinking Machines' Qwen3-8B test, an improved deterministic build took 42 s against 26 s for vLLM's default, and SGLang reports an average 34.35% slowdown on its FlashInfer and FlashAttention 3 backends. Performance & compatibility ^{7 9}
  • Coverage is incomplete: the bit-exact emulator targets dense blocks on NVIDIA GPUs and excludes mixture-of-experts inference and training, and vLLM's batch-invariant mode is in beta, with open work on AMD hardware and speculative decoding. Performance & compatibility ^{6 10 17}
  • Amodo's status page for the AI 2040 verification plan rates a reproducible inference stack for that plan as 'not started'. Performance & compatibility ¹⁸
  • Exact replay requires the prover to disclose weights, software versions, parallelism and batch sizes to whoever recomputes. Privacy & leakage ^{6 16}

From the family or selected implementation's record. ?

Model weights

Depends on the design for Proofs of useful work for capacity accounting and Deterministic and bit-exact inference.

Inputs and outputs

Depends on the design for Proofs of useful work for capacity accounting and Deterministic and bit-exact inference.

Training data

Not involved: Proofs of useful work for capacity accounting and Deterministic and bit-exact inference.

Proofs of useful work for capacity accounting

• R3 Pearl proof-of-useful-work blockchain Open-source project, Pearl Research Labs

Deterministic and bit-exact inference

• R2 Batch-invariant inference kernels (Thinking Machines) Open-source project, Thinking Machines Lab
• R3 Verde and RepOps (Gensyn) Product, Gensyn
• R1 Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute

1. Pacing AI Requires Proof, Attestable (2026). Original
2. Mechanisms to Verify International Agreements About AI Development, A. Scher & L. Thiergart (2025). Original
3. Proofs of Useful Work from Arbitrary Matrix Multiplication, I. Komargodski & O. Weinstein (2025). Original
4. Pearl Floating Point Scheme Specification, Pearl Research Team (2026). Original
5. pearl: Monorepo for the Pearl network, Pearl Research Labs (2026). Original
6. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
7. Defeating Nondeterminism in LLM Inference, H. He & Thinking Machines Lab (2025). Original
8. Hawkeye: Reproducing GPU-Level Non-Determinism, E. Badash et al. (2026). Original
9. Towards Deterministic Inference in SGLang and Reproducible RL Training, The SGLang Team (2025). Original
10. Batch Invariance (vLLM documentation), vLLM project (2026). Original
11. gensyn-ai/ree: Gensyn Reproducible Execution Environment (GitHub repository), Gensyn (2026). Original
12. EigenCloud Brings Verifiable AI to Mass Market with EigenAI and EigenCompute Launches, EigenCloud (2025). Original
13. Building Delphi: Pricing, Settlement, and Agentic Trading, D. Jedamski (2026). Original
14. Reproducible Execution Environment (REE) (Gensyn documentation), Gensyn (2026). Original
15. What is Delphi? (Delphi documentation), Gensyn (2026). Original
16. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
17. [Feature]: Batch Invariant Feature and Performance Optimization (vLLM issue #27433), vLLM project contributors (2025). Original
18. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original