Shmidman, S., Fredman, A., Sudakov, O., & Bendris, M. (2025). Learning to Reason: Training LLMs with GPT-OSS or DeepSeek R1 Reasoning Traces.
Chicago Style (17th ed.) CitationShmidman, Shaltiel, Asher Fredman, Oleg Sudakov, and Meriem Bendris. Learning to Reason: Training LLMs with GPT-OSS or DeepSeek R1 Reasoning Traces. 2025.
MLA (9th ed.) CitationShmidman, Shaltiel, et al. Learning to Reason: Training LLMs with GPT-OSS or DeepSeek R1 Reasoning Traces. 2025.
Warning: These citations may not always be 100% accurate.