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

Spanish

Bitcoin-style Proof-of-Work (PoW) protege blockchains sin permiso, pero gasta un cálculo sustancial en puzzles de hash que no tienen otra utilidad que extender la cadena. Al mismo tiempo, hemos visto que el aumento de la IA generativa ha creado una demanda significativa de recursos computacionales que, por desgracia, solo están disponibles para unos pocos jugadores. Proponemos una solución que resuelva ambos problemas al mismo tiempo. En particular, presentamos Proof-of-ML-Inference (PoML), un protocolo de consenso en el que los mineros realizan inferencias de aprendizaje automático solicitadas por el usuario como parte de su algoritmo de consenso. Identificamos exactamente qué suposiciones computacionales son necesarias para la inferencia ML para reemplazar de forma segura el trabajo de hash, formalizar esas

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