I think maybe this is the paper you're looking for?

https://arxiv.org/abs/2009.03393

On Tuesday, January 24, 2023 at 1:51:17 PM UTC [email protected] wrote:

> Is there any information on the success rate of GPT-based provers on 
> theorems in different sections of the metamath database? I am particularly 
> interested in the very beginning, i.e., the part on propositional logic. I 
> remember some paper saying that it is higher towards the beginning, but I 
> can't find it now.

-- 
You received this message because you are subscribed to the Google Groups 
"Metamath" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To view this discussion on the web visit 
https://groups.google.com/d/msgid/metamath/ad845be6-9793-4cf7-80a9-1ad4bf92df3bn%40googlegroups.com.

Reply via email to