Metraipolis › archive › dc_fac2aae020da

StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean — arXiv:2609.09264

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.09264
License (as archived): CC0-1.0
Archived: 2026-10-16T07:50:51.904Z
SHA-256 of the archived text: 6b99dfd28bfd916a518d0ca63d4b2114701e844b8e595b2d6be044cb05d2e946
Stable URL of this page: https://metraipolis.com/documento/dc_fac2aae020da

How to cite

StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean — arXiv:2609.09264 — arXiv (en), https://arxiv.org/abs/2609.09264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fac2aae020da (Metraipolis archive dc_fac2aae020da, sha256 6b99dfd28bfd916a518d0ca63d4b2114701e844b8e595b2d6be044cb05d2e946)

BibTeX

@misc{dcfac2aae020da,
  title = {StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean — arXiv:2609.09264},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09264},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fac2aae020da; sha256 6b99dfd28bfd916a518d0ca63d4b2114701e844b8e595b2d6be044cb05d2e946},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Leading benchmarks for formal theorem proving with large language models are small collections drawn from competition math, such as the IMO and Putnam, that poorly represent field-specific applications. We introduce StochBench, a Lean 4 benchmark of 450 graduate stochastic-processes problems at varying abstraction levels, each paired with its natural-language source. Addressing a field underrepresented in Mathlib, it covers finite and countable Markov chains, renewal processes, random walks, martingales, stopping times, queues, Brownian motion, stochastic calculus, weak convergence, and Poisson and continuous-time Markov processes. Our Opus 4.8-based agent achieves a 34.9% proof rate (157/450) under a 15-minute per-problem limit. StochBench better represents domain-specific applied mathematics while remaining challenging for advanced provers.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2609.09264 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T07:24:00.863Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).