A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Mohsen Hariri, Weicong Chen, Nahal Shahini, et al.
This paper formalizes test-time scaling in reasoning LLMs into three structural regimes and proposes evaluation principles, reproducibility requirements, and a large dataset of reasoning traces.
Unknown
This study evaluates small language models using standardized benchmarks and publicly available datasets, ensuring transparency and reproducibility.
Unknown
This paper shows that benchmark evaluations of reasoning models are highly unstable, with minor condition changes causing large result variations that undermine reproducibility.
Unknown
Dolma is an open corpus of three trillion tokens for language model pretraining, designed to support transparency and reproducibility in AI research.