This research paper attempts a common encoding in Lean 4 for Lob's Theorem, reflective programming, and acausal decision theory. It is a skeletal-encoding-discovery paper examining a META-DB observation, not a proof of a new theorem or a resolution of the source problems.
This research introduces a novel learning-to-refine framework to address the prohibitive computational cost of Large Language Models (LLMs) in formal theorem proving. By exploiting compiler outputs that compress diverse proof attempts into structured failure modes, the method enables efficient proof exploration and local error correction, significantly amplifying the reasoning capabilities of base provers.
This paper introduces a formally verified framework for patent analysis, employing a hybrid AI and Lean 4 pipeline. It marks the first known application of interactive theorem proving to intellectual property analysis, addressing the shortcomings of manual or probabilistic methods.
DreamProver introduces an agentic framework using a wake-sleep program induction paradigm to discover reusable lemmas for formal theorem proving. It iteratively evolves a compact, transferable lemma library, significantly improving performance on unseen theorems.