Reproduce “Proof-of-Machine-Learning-Inference: Mining Knowledge, Not Hashes” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Wan Ki Wong, Michele Ciampi, Rik Sarkar
PoML uses user-requested machine-learning inference as mining work, with miners answering queries and proving their outputs as part of the block race. Its security argument depends on computational independence and stated assumptions. In a 50-block, single-host simulation, PoML averaged 299.19-second block intervals with a 220-second standard deviation, versus 294.06 seconds and 266 seconds for PoW; this is not a live-network guarantee.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.