Our main contributions are as follows.

In theorem proving, the task of selecting useful premises from alarge library to unlock the proof of a given conjecture is crucially important. This presents a challenge foralltheorem provers,especially theonesbasedonlanguage models, due to their relative inability to reason over huge volumes of premises in text form.

End-to-end learnable discrete-continuous models are compositional, tend togeneralize better,and are more interpretable.