Implementation · Verde and RepOps (Gensyn)
Evidence & limits
On this page
R3In production for reproducing declared-model inference from receipts in Gensyn's information-market service
Gensyn reports using its public runtime in production to settle markets whose answers anyone can re-run, but all evidence of that use comes from Gensyn, and no independent security evaluation of Verde or RepOps has been published.
Assessed use: reproducing declared-model inference from receipts in Gensyn's information-market service
Rubric assessment
- R1 met: the paper states the claim, that the client obtains the correct result if at least one provider is honest, together with the dispute protocol and its assumptions 1.
- R2 met: Gensyn's Reproducible Execution Environment, which runs LLM inference with RepOps and writes receipts for re-execution, is public as binaries with an MIT-licensed SDK 4. The paper measures RepOps on NVIDIA T4, RTX 3090 and A100 GPUs, including Llama-8B inference and fine-tuning on an A100, against a stated adversary: dishonest compute providers 1. The paper's evaluation reports overheads. The claim of bitwise-identical results across hardware comes from Gensyn's posts 2.
- R3 met on the provider's own account, as a production service that others can check. Gensyn reports that Delphi, its information-market app, is live on its mainnet, that hosted REE settlement is available for partner markets, and that markets settled by open models inside REE produce receipts anyone can re-run to verify the answer 5. The May 2026 post describes no dispute process. Gensyn's service documentation also describes the REE judge receipts and mainnet deployment 7. REE's README lists v0.8.0, released on 5 October 2026, and Gensyn does not label its releases alpha or beta 4 6. Gensyn also states that Verde and RepOps are deployed in Judge, its AI evaluation service, without saying how Judge uses them 2 3. No party other than Gensyn is documented relying on Verde or REE for a verification decision. The production account covers receipt re-execution. It does not document how Verde's guarantee that one honest provider suffices is applied in that service 5 7.
- R4 not met: no independent audit, red-team or peer-reviewed security analysis has been published.
Confidence is low: R3 rests on Gensyn's own posts, and REE's documentation warns that receipts from one release may not re-verify under the next 6.
- An independent public security evaluation of the Verde dispute protocol and of RepOps reproducibility across hardware, which the paper asserts but does not test.
Assessed 2026-10-08 against rubric v1.1.
Evidence
- The paper reports RepOps overheads against PyTorch on NVIDIA T4, RTX 3090 and A100 GPUs, for DistilBERT and Llama models 1. For Llama-8B on an A100 with 80 GB, RepOps added 98% to inference time and 126% to LoRA fine-tuning time 1.
- Gensyn reports that RepOps gives bitwise-identical results across hardware, and that Verde and RepOps are deployed in Judge 2. Gensyn introduced Judge in August 2025 with a reasoning task framed as a prediction market 3.
- Gensyn reports that Delphi is live on its mainnet, that markets settled by open models inside REE produce a receipt that anyone can re-run, and that hosted REE settlement is available for partner markets 5.
- REE is public as an MIT-licensed SDK with proprietary binaries 4. Its release notes add pipeline parallelism for models of up to 72B parameters 4, and its documentation describes reproducible int8 attention and mixture-of-experts kernels 6. Version 0.8.0 was released on 5 October 2026 4.
Limitations
- The guarantee needs at least one honest provider. The authors state that if all providers are dishonest, the referee accepts an incorrect output 1.
- The paper's RepOps supports 32-bit floating point only, and reproducibility only when each setup runs the program on a single GPU 1. Gensyn reports that REE has since added pipeline parallelism and int8 attention 4 6.
- Receipts are tied to an REE release. Each recent release warns that some receipts from the one before may not re-verify, most recently v0.7.0 receipts under v0.8.0 4.
- Gensyn states that Verde shows the output was produced by the declared model and data, not that the model itself is correct 2.
- The RepOps kernels ship only as binaries under a proprietary licence 4.
- All evidence of production use comes from Gensyn 2 3 5.
Blockers
Reproducibility costs throughput: RepOps added 98% to Llama-8B inference time on an A100 in the paper, and Gensyn reports a threefold cut in REE's reproducible-mode overhead without absolute figures.
The providers who re-run a job and the referee need the model and data, and the guarantee holds only if at least one provider is honest.