Pearl is a proof-of-useful-work blockchain developed by Pearl Research Labs whose mining is designed to be a by-product of the matrix multiplications that AI models perform on GPUs.
Its live network launched with an integer scheme, and its code is public. Pearl's September 2026 specification describes an FP8 version. Pearl reports that an integer-scheme mining variant of a 70-billion-parameter model served more tokens per second on four H200 GPUs than the original model, in a benchmark that does not isolate the cost of mining.
An independent study of the integer-scheme network in May 2026 found that its dominant mining software appears to multiply random matrices, which verification does not distinguish from AI work. Pearl is in operational use for blockchain consensus, not for checking how AI hardware is used. Its security rests on new hardness assumptions, and Pearl lists known shortcuts that let miners do less work than nominal.
R3 for checking claims of matrix-multiplication work in blockchain consensus. The network is live, but no independent security evaluation exists, and the capacity-bounding use in Proofs of useful work for capacity accounting is not demonstrated.
Assessed use: checking matrix-multiplication work proofs for blockchain consensus
On this page
What it is
Pearl is a layer-1 blockchain developed by Pearl Research Labs. It replaces hash-based mining with a proof of useful work built on matrix multiplication 2 4. The chain launched with an integer scheme 2.
Pearl's September 2026 specification describes a protocol "in which the unit of mining work is FP8 matrix multiplication on GPUs" 1. This extends the integer proof of useful work of Komargodski and Weinstein 1 5. Komargodski is at Pearl Research Labs 7.
Pearl presents the scheme as "2-for-1": GPUs produce proof of work "as a side-effect of AI training and inference workloads" 2. Its public monorepo contains several components 4:
- a reference full node;
- a vLLM-based GPU miner;
- a Plonky2/STARKy-based proof-of-work circuit and verifier.
How it works
Mining. In the FP8 specification, a miner multiplies matrices of its choosing, which Pearl describes as "the operands of an AI training or inference workload" 1. Each block involves four steps 1:
- Low-rank noise matrices are derived from public seeds.
- The noised product is computed in quantised FP8.
- Output tiles are hashed as lottery tickets.
- A tile that meets the target wins the block, with expected wins proportional to work.
The miner then subtracts lower-order correction terms to recover the useful product "at FP8-level accuracy" 1.
Checks on winning tiles. A jackpot policy approves a winning tile only when several statistical checks pass. These checks are meant to exclude degenerate inputs 1.
Verification. The FP8 verifier "checks one tile of the matmul, never the whole product" 1. It recomputes that tile bit for bit, reproducing the GPU's rounding and accumulation order off the GPU with the technique of Badash et al. 1 7. A zero-knowledge verifier can keep the miner's operand data private while proving that the tile satisfies the protocol rules 1. The integer whitepaper describes hash-based SNARKs (Plonky2), compressed to "below 60KB" by recursion 2. An appendix to the FP8 specification extends verification to mixture-of-experts layers 1.