Search Results for author:
Found 4 papers, 0 papers with code
BAIT: Benchmarking (Embedding) Architectures for Interactive Theorem-Proving
We also provide a qualitative analysis, illustrating that improved performance is associated with more semantically-aware embeddings.
TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning.
MoonLight: Effective Fuzzing with Near-Optimal Corpus Distillation
We then compare the effectiveness of ML-distilled seed selection in a long campaign, comparing against cmin, with ML configured to give weight to different characteristics of the seeds (ie, unweighted, file size, or execution time), as well as against each target's full corpus and a singleton set containing only an "empty" valid input seed.
Cryptography and Security
TacticToe: Learning to Prove with Tactics
We implement a automated tactical prover TacticToe on top of the HOL4 interactive theorem prover.
