{"type":"link","version":"1.0","title":"Beyond Accuracy: A Multidimensional Evaluation of Statistical Reasoning in Large Language Models","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2608.03038","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2608.03038.png","thumbnail_width":1200,"thumbnail_height":630}