How has the credibility revolution shaped political science? We address this question by classifying 91,632 articles published between 2003 and 2023 across 156 political science journals using large language models, focusing on research design, credibility-enhancing practices, and citation patterns. We find that design-based studies -- those leveraging plausibly exogenous variation to justify causal claims -- have become increasingly common and receive a citation premium. In contrast, model-based approaches that rely on strong modeling assumptions have declined. Yet the rise of design-based work is uneven: it is concentrated in top journals and among authors at highly ranked institutions, and it is driven primarily by the growth of survey experiments. Other credibility-enhancing practices that help reduce false positives and false negatives, such as placebo tests and power calculations, remain rare. Taken together, our findings point to substantial but selective change, more consistent with a partial reform than a revolution.

翻译：可信度革命如何塑造了政治科学？我们通过使用大语言模型对2003年至2023年间发表在156种政治学期刊上的91,632篇文章进行分类来探讨这个问题，重点关注研究设计、可信度提升实践和引用模式。我们发现，基于设计的研究——即利用近似外生变异来论证因果主张的研究——已变得越来越普遍，并获得了引用溢价。相比之下，依赖强建模假设的基于模型的方法则有所减少。然而，基于设计工作的兴起并不均衡：它主要集中在顶级期刊和顶尖机构的作者中，并且主要由调查实验的增长所驱动。其他有助于减少假阳性和假阴性的可信度提升实践，如安慰剂检验和功效计算，仍然较为罕见。综上所述，我们的研究结果表明，变化是显著但选择性的，更符合局部改革而非一场革命。