01 / The mechanism and its boundary
What is being described
Pearl Research Labs describes itself as building infrastructure and algorithms for AI inference S-3603. It develops the Pearl blockchain, an instance of proofs of useful work:
- Protocol specification. Pearl specifies a proof-of-useful-work protocol in which the unit of mining work is FP8 matrix multiplication on GPUs S-1105.
- Integer whitepaper. Its earlier whitepaper presents mining as a side-effect of the matrix multiplications in AI training and inference workloads S-1106.
- Open-source network. Pearl publishes a monorepo with a reference full node, a vLLM-based GPU miner and a proof-of-work circuit and verifier S-1107. Its README says the mining follows the proof of useful work from arbitrary matrix multiplication proposed by Komargodski and Weinstein S-1107 S-1609.
- Reproducible GPU arithmetic. Pearl and Stanford researchers published Hawkeye at MLSys 2026 S-1010. It re-executes on a CPU, bit for bit, the matrix multiplications that NVIDIA Ampere, Hopper and Ada Lovelace GPUs perform in FP16, BF16 and FP8 S-1010; see Deterministic and bit-exact inference.
Connections in the research map
Related research
Sources and provenance
- S-3603 / Tier B
Pearl Research Labs homepage ↗
· 2026 · Pearl Research Labs
Supports: infrastructure and algorithms for AI inference
Version and catalogue details - S-1105 / Tier B
Pearl Floating Point Scheme Specification ↗
Pearl Research Team · 2026 · Pearl Research Labs
Supports: FP8 proof-of-useful-work protocol specification
Version and catalogue details - S-1106 / Tier B
Pearl INT Whitepaper ↗
Pearl Research Labs · 2026 · Pearl Research Labs
Supports: integer matrix-multiplication whitepaper; mining as a side-effect of AI workloads
Version and catalogue details - S-1107 / Tier B
pearl: Monorepo for the Pearl network ↗
Pearl Research Labs · 2026 · GitHub
Supports: public monorepo: full node, GPU miner, proof-of-work circuit and verifier; README cites the Komargodski-Weinstein proposal
Version and catalogue details - S-1609 / Tier B
Proofs of Useful Work from Arbitrary Matrix Multiplication ↗
I. Komargodski, O. Weinstein · 2025 · arXiv
Supports: proof of useful work from arbitrary matrix multiplication (Komargodski and Weinstein)
Version and catalogue details - S-1010 / Tier A
Hawkeye: Reproducing GPU-Level Non-Determinism ↗
E. Badash, D. Boneh, I. Komargodski, M. Srivastava · 2026 · Proceedings of Machine Learning and Systems 8 (MLSys 2026)
Supports: Hawkeye (MLSys 2026): two of four authors at Pearl Research Labs; bit-exact CPU replay of GPU matrix multiplication
Version and catalogue details
- Source review date
- 2026-10-08
- Drafted by (source map)
- ai
- Review handles (source map)
- codex-review