arXiv:2607. 08986v2 Announce Type: replace Abstract: We formalize a research result in the Lean 4 proof assistant by having a mathematician direct an AI system, and frame the activity as a formalization game.
arXiv:2607. 08986v1 Announce Type: new Abstract: We formalize a research result in the Lean 4 proof assistant by having a mathematician direct an AI system, and frame the activity as a formalization game.
arXiv:2610.08144v1 Announce Type: cross Abstract: Autoformalisation is increasingly used to verify mathematical texts, including those generated by AI, as in OpenAI's announced proof of blow-up of so...
arXiv:2606. 31134v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated exceptional capabilities in mathematical reasoning, they frequently produce subtle errors that evade human detection.
arXiv:2606. 28572v1 Announce Type: cross Abstract: The axiom of choice has divided the foundations of mathematics for over a century, but the distinction between classical and constructive proofs has remained a philosophical and methodological one.
The paper introduces h1, a simple agentic loop that interfaces a language model with Lean 4, avoiding complex human-designed workflows. h1 achieves state‑of‑the‑art performance on benchmarks such as PutnamBench, FATE‑X, and FormalConjectures100‑Solved, solving eight open problems and matching or surpassing specialized systems like Goedel‑Architect and AlphaProof Nexus. Experiments show that an efficient Lean interface is crucial for cost and success, suggesting that future evaluations should prioritize execution feedback over elaborate workflows.
arXiv:2610.17090v1 Announce Type: cross Abstract: On 6 October 2026 OpenAI published an initial 722 AI-written mathematical manuscripts, organized into 372 problem families, in the public repository...
The paper proposes five axioms that formalize the assumptions underlying systematic trading, each expressed through declared quantitative constants. It demonstrates that these axioms necessitate a five‑stage canonical structure for a quantitative investment system and proves that omitting any stage worsens performance under the axioms. Empirical tests on real market data show that the axioms hold, though certain declared constants (e.g., κ = 1 and an exponential decay assumption) are rejected.
arXiv:2607. 06341v1 Announce Type: cross Abstract: Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers such as Coq require enormous expert effort.
arXiv:2606. 05400v1 Announce Type: cross Abstract: Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context decays, and local repairs corrupt distant work.
MathAdv is a diagnostic benchmark for formal theorem proving that covers 13 undergraduate- and graduate-level mathematics domains. It includes Lean 4 proofs and up to three auxiliary tasks—multiple-choice questions, fill-in-the-blank problems, and expert-crafted transformations—to probe knowledge, informal reasoning, and robustness to problem presentation. Evaluation of current theorem provers shows formalization is a major bottleneck, performance varies by domain, natural-language guidance can help or hinder models, and equivalent reformulations reveal significant robustness gaps.
Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers such as Coq require enormous expert effort. Large language models (LLMs) promise to generate these proofs automatically, yet existing approaches wire a fixed, human-designed proof strategy into the system and constrain the model to follow it (retrieving premises and predicting tactics one step at a time, or splitting goals by divide-and-conquer), and still prove only a fraction of their target theorems.
arXiv:2608.28997v1 Announce Type: new Abstract: In May 2026 an OpenAI model produced a counterexample to the Erd\H{o}s unit distance conjecture. Five mathematicians published a human-verified version...