🧪 Test?View on arXiv
StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean
Not provided
benchmarkingstochastic processesformal theorem proving
2609.09264
Builder Relevance
1h ago70%
Abstract
StochBench is a Lean 4 benchmark of 450 graduate stochastic-processes problems at varying abstraction levels, each paired with its natural-language source.
Reality Card
Core Claim
StochBench introduces a comprehensive benchmark for stochastic processes that better represents domain-specific applied mathematics compared to existing benchmarks.
Method / Result
The Opus 4.8-based agent achieved a 34.9% proof rate (157/450) under a 15-minute per-problem limit.
Limitations
The benchmark may not fully capture the complexity of all stochastic processes, potentially limiting its applicability.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.