Scaling In, Not Up? Supplementary Material

This dataset contains the supplementary materials for the paper “Scaling In, Not Up? Testing Thick Citation Context Analysis with GPT-5 and Fragile Prompts,” available at https://arxiv.org/abs/2602.22359 and forthcoming as a chapter in: Simons A, Wüthrich A, Zichert M, et al. (eds) (2026) Understanding Science with Large Language Models? Potentials for the History, Philosophy, and Sociology of Science. Bielefeld: transcript. Available at: https://www.transcript-publishing.com/978-3-8376-7994-6/understanding-science-with-large-language-models. The files include materials used in the preparation, analysis, and documentation of the study. The supplementary sections referenced in the paper are contained in Supplementary-Sections.pdf.本数据集包含论文《向内拓展，而非向上扩容？基于GPT-5与脆弱提示词的深度引用语境分析测试》（Scaling In, Not Up? Testing Thick Citation Context Analysis with GPT-5 and Fragile Prompts）的补充材料，该论文可通过https://arxiv.org/abs/2602.22359获取，且即将作为章节收录于以下著作： Simons A、Wüthrich A、Zichert M 等（编）(2026) 《以大语言模型（Large Language Model）理解科学：科学史、科学哲学与科学社会学的发展潜力》，比勒费尔德：transcript出版社。该著作可通过https://www.transcript-publishing.com/978-3-8376-7994-6/understanding-science-with-large-language-models查阅。 本数据集所收录的文件涵盖了本研究在筹备、分析与文档编制各环节所使用的相关材料。论文中提及的补充章节均收录于Supplementary-Sections.pdf文件中。