🧪 Test?View on arXiv
OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery
Not specified in the abstract
benchmarkingresearch problemslarge language modelsscientific rediscovery
2610.37739
Builder Relevance
2h ago80%
Abstract
OpenFrontiers introduces a structured corpus of open research problems and a benchmark for evaluating large language models on research-level problem solving.
Reality Card
Core Claim
OpenFrontiers provides a comprehensive resource linking a corpus of 12,151 open research problems with a benchmark of 200 problems for evaluating LLMs in scientific rediscovery.
Method / Result
Closed-book rediscovery was rare, with at most 7 of 40 resolved problems successfully rediscovered.
Limitations
The evaluation protocol's reliance on closed-book conditions may limit reproducibility of results.
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.