Newest papers

Proof-of-Machine-Learning-Inference: Mining Knowledge, Not Hashes

Wan Ki Wong, Michele Ciampi, Rik Sarkar · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26713 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Bitcoin-style Proof-of-Work (PoW) melindungi blockchains tanpa izin tetapi menghabiskan perhitungan substansial pada puzzle hash yang tidak memiliki utilitas selain memperluas rantai. Pada saat yang sama, kami telah melihat bahwa munculnya generatif AI telah menciptakan permintaan yang signifikan untuk sumber daya komputasi yang sayangnya hanya tersedia untuk beberapa pemain. Kami mengusulkan solusi yang memecahkan kedua masalah pada saat yang sama. Secara khusus, kami menyajikan Proof-of-ML-Inference (PoML), protokol konsensus di mana para penambang melakukan inferensi pembelajaran mesin yang diminta pengguna sebagai bagian dari algoritma konsensus mereka. Kami mengidentifikasi persis asumsi komputasi apa yang dibutuhkan untuk inferensi ML untuk aman menggantikan hash kerja, mengformalisasi asumsi tersebut, dan memberikan bukti bahwa LLM dan model difusi memuaskan mereka.

Machine translation (Meta M2M100); the English original follows.

Abstract

Bitcoin-style Proof-of-Work (PoW) secures permissionless blockchains but spends substantial computation on hash puzzles which have no utility other than extending the chain. At the same time, we have seen that the rise of generative AI has created significant demand for computational resources that are unfortunately available only to a few players. We propose a solution that solves both problems at the same time. In particular, we present Proof-of-ML-Inference (PoML), a consensus protocol in which miners perform user-requested machine-learning inference as part of their consensus algorithm. We identify exactly what computational assumptions are needed for ML inference to safely replace hash work, formalize those assumptions, and give evidence that LLMs and diffusion models satisfy them. We then formally analyse the security of our protocol by reducing the security of our protocol to the security of the Bitcoin Backbone model. Finally, we empirically evaluate block-time stability, showing that, in a simulated environment, PoML maintains a block production rate close to its calibrated block-time target.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Hash function, Protocol (science), Inference, Block (permutation group theory), Theoretical computer science

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange