We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
We propose an online training procedure for a transformer-based automated theorem prover. Our approach leverages a new search algorithm, HyperTree Proof Search (HTPS), inspired by the recent success of AlphaZero. Our model learns from previous proof searches through online training, allowing it to generalize to domains far from the training distribution. We report detailed ablations of our pipeline's main components by studying performance on three environments of increasing complexity. In particular, we show that with HTPS alone, a model trained on annotated proofs manages to prove 65.4% of a held-out set of Metamath theorems, significantly outperforming the previous state of the art of 56.5% by GPT-f. Online training on these unproved theorems increases accuracy to 82.6%. With a similar computational budget, we improve the state of the art on the Lean-based miniF2F-curriculum dataset from 31% to 42% proving accuracy.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.11491")
get_code_for_paper("2205.11491")
have("2205.11491")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.11491.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.11491)
Connect an agent — have() is free.