Proposal Explorer

Add claims to see which ones the mechanisms address.

Not counted

Excluded by your filters: Deterministic and bit-exact inference and Bandwidth limits and compartmentalization

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

• Deterministic and bit-exact inference: Analysis · excluded by filters
• Bandwidth limits and compartmentalization: Analysis · excluded by filters

Excluded by your filters

• Deterministic and bit-exact inference Attack testing is analysis; the filter asks for at least red-teamed.
• Bandwidth limits and compartmentalization Attack testing is analysis; the filter asks for at least red-teamed.

Open significant flaws

6 flaws in 2 mechanisms

• 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. ^{1 3}

  Open question · Significant · Open. On the record

• Low-communication training reduces the bandwidth training needs in Bandwidth limits and compartmentalization

  DiLoCo matched fully synchronous training on 8 workers while communicating 500 times less. Rahman writes that this family of methods theoretically allows large-scale training with less than 100 Mbps. Lucid includes these methods in its bounds, but notes that extreme activation compression, architectures with unusually small inter-layer widths, or modular paradigms could erode the margin. ^{13 16 17}

  Theoretical argument · Significant · Open. On the record

• Operator control of pod routing collapses the bound in Bandwidth limits and compartmentalization

  Lucid's analysis finds that if the operator can freely assign pods to routers, it could dedicate a whole cell of 100 or more pods to one pipeline stage. The bound then falls to about 90–220x uncompressed and as low as about 25x with compression. The proposed mitigation, auditor-controlled random assignment that is periodically re-randomized, has not been implemented. ¹³

  Theoretical argument · Significant · Open. On the record

• Undeclared local storage raises per-pod capacity in Bandwidth limits and compartmentalization

  More memory or storage per pod helps an adversary. Lucid requires per-pod storage to be declared, capped and physically inspected. ¹³

  Theoretical argument · Significant · Open. On the record

• Training within one pod is not covered in Bandwidth limits and compartmentalization

  Lucid's bounds concern pre-training models larger than the pods are sized for. Training models that fit in one pod, fine-tuning and reinforcement-learning post-training within one pod are outside the modelled threat. ¹³

  Open question · Significant · Open. On the record

• Parallel scale-up switches are hard enforcement points in Bandwidth limits and compartmentalization

  In GB200 topologies, GPUs reach GPUs in other nodes through NVSwitches without a NIC on the path. Amodo notes that limits are hard to enforce there because many switches work in parallel, so compromising one or two would bypass the limit. ¹⁵

  Theoretical argument · 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. ¹

  Open question · Minor · Open. On the record

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

• R2 Tamper evidence for verifier devices Add

  Excluded by filters: attack testing: analysis

  • Bandwidth limits and compartmentalization waits on it. Shaping devices and routing assignments must be trusted by both parties; Amodo has not yet fully analysed resilience to a compromised DPU.
• R1 Network taps and certifiers Add

  Excluded by filters: attack testing: analysis

  • Bandwidth limits and compartmentalization waits on it. The verifier must know that all traffic leaving a pod crosses the capped, monitored links.

Missing prerequisites

• R2 Tamper evidence for verifier devices needed by Bandwidth limits and compartmentalization Add

Blockers

8 blockers recorded

• 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 ^{2 4}
  • 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 ^{1 5 18}
  • Amodo's status page for the AI 2040 verification plan rates a reproducible inference stack for that plan as 'not started'. Performance & compatibility ¹⁹
  • Exact replay requires the prover to disclose weights, software versions, parallelism and batch sizes to whoever recomputes. Privacy & leakage ^{1 11}
• Bandwidth limits and compartmentalization
  • No cap that a verifier can check has been implemented or red-teamed. Adversarial validation ¹³
  • The verifier must know that all traffic leaving a pod crosses the capped, monitored links. Coverage & hidden compute. Waits on Network taps and certifiers ¹¹
  • Shaping devices and routing assignments must be trusted by both parties; Amodo has not yet fully analysed resilience to a compromised DPU. Hardware trust. Waits on Tamper evidence for verifier devices ^{13 15}
  • Advances in low-communication training could shrink the margin that the cap enforces. Capacity bounds ^{13 16 17}

From the family or selected implementation's record. ?

Model weights

Depends on the design for Deterministic and bit-exact inference.

Not involved: Bandwidth limits and compartmentalization.

Inputs and outputs

Depends on the design for Deterministic and bit-exact inference.

Not involved: Bandwidth limits and compartmentalization.

Training data

Not involved: Deterministic and bit-exact inference and Bandwidth limits and compartmentalization.

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

Bandwidth limits and compartmentalization

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• R1 RAND secure inference data center (SIDC) design Proposed architecture, RAND

1. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
2. Defeating Nondeterminism in LLM Inference, H. He & Thinking Machines Lab (2025). Original
3. Hawkeye: Reproducing GPU-Level Non-Determinism, E. Badash et al. (2026). Original
4. Towards Deterministic Inference in SGLang and Reproducible RL Training, The SGLang Team (2025). Original
5. Batch Invariance (vLLM documentation), vLLM project (2026). Original
6. gensyn-ai/ree: Gensyn Reproducible Execution Environment (GitHub repository), Gensyn (2026). Original
7. EigenCloud Brings Verifiable AI to Mass Market with EigenAI and EigenCompute Launches, EigenCloud (2025). Original
8. Building Delphi: Pricing, Settlement, and Agentic Trading, D. Jedamski (2026). Original
9. Reproducible Execution Environment (REE) (Gensyn documentation), Gensyn (2026). Original
10. What is Delphi? (Delphi documentation), Gensyn (2026). Original
11. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
12. Verification Plan, R. Dean (2026). Original
13. Traffic Shaping for Workload Classification, Lucid Computing (2026). Original
14. De-risking Interconnect Limits for AI Verification, A. Scher et al. (2026). Original
15. The Tray as a Bandwidth Boundary, Amodo Design (2026). Original
16. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). Original
17. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). Original
18. [Feature]: Batch Invariant Feature and Performance Optimization (vLLM issue #27433), vLLM project contributors (2025). Original
19. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original