Researchers have developed a method to evaluate the quality of scientific papers based on their titles and abstracts. The approach uses various text analysis techniques, including word embeddings and neural networks, to classify papers as high-quality or flawed. The study found that a combination of SBERT embeddings and a neural network achieved an accuracy rate of 87.22% in distinguishing between highly cited and retracted papers. This work has implications for the development of tools that promote academic integrity and trustworthy scholarship. --- Why it matters: This research matters to AI engineers because it demonstrates how text analysis techniques can be used to evaluate the quality of scientific papers, which is a crucial aspect of academic integrity. The findings have potential applications in developing tools that help identify flawed studies and promote trustworthy scholarship. Source: https://arxiv.org/abs/2608.20368