Browse Articles

Machine learning systems are often expected to make fair decisions, yet the most widely used fairness criteria—independence, separation, and sufficiency—cannot generally be satisfied at the same time. In this study, students tested these criteria using a logistic regression model on a real-world student performance dataset and found that each criterion was met only at different prediction thresholds, with no threshold satisfying all three simultaneously. These results illustrate the inherent trade-offs in algorithmic fairness and highlight why achieving perfectly fair machine learning models is often impossible in practice.

Large language models are increasingly used to solve math problems, but their ability to handle multi-step reasoning remains uncertain. In this study, students tested whether different prompting styles could improve LLM accuracy on challenging AIME math questions and found that detailed step-by-step solutions did not significantly outperform simpler prompts. These results suggest that improving LLM mathematical reasoning may require deeper model-level advances rather than changes in prompting style alone.

This study strongly illustrates that optimizing 3D printing parameters would enhance a triboelectric nanogenerator's performance. The design improvements substantiate the potential of optimized, 3D-printed TENGs for developing scalable, cost-effective solutions for powering low-energy electronics, particularly in applications such as structural health monitoring.

The purpose of this study was to determine the necessity of previous non-algorithmic attacks (Adversarial Training) in light of algorithmic defense methods (Gradient Masking and Defensive Distillation) against FGSM attacks. We found a significant increase in image classification accuracy from defense methods with the non-algorithmic defense method compared to ones without. By analyzing the significance with a McNemar test, we determined that the inclusion of non-algorithmic defense methods is still necessary in light of new algorithmic defense methods.

This manuscript tackles a major social issue in the health news sector, with social media being one of the primary sources of information and a prime spot to propagate fake news. The author proposes X-HND , which is a unique architecture that combines emotional and contextual analysis in a Graph Neural Network to accurately detect fake news. This was a multi-step process which involved the creation of a custom health news dataset (HNDataset), and an emotional variant that uses RoBERTa to extract emotion. These dataset were then used to prove the hypothesis that accuracy increases when the custom dataset is used to train the model and that with the integration of emotion capture, the detection accuracy increases further.

This paper discusses how the conditions at the center of stars affects the nuclear reactions that happen inside these stars. We focused on the effect of temperature and density and found that these two properties interacted to create a greater effect when combined than when separate.

The authors looked at how different blends of synthetic and non-synthetic fabrics protected against UV radiation.

Online review platforms often provide different reviews on the same product, potentially confusing consumers. In this study, we found that the number of raters on Amazon is lower for the same book, while ratings on Amazon were higher than those on Goodreads. Furthermore, these differences in ratings and rater counts were larger for fiction books than for non‑fiction books.

This study investigated perceptions of the emerging workforce toward the use of artificial intelligence in hiring, specifically for assessing subjective "culture fit." Through a mixed-methods survey of 150 high school and early-college students in Nepal, we found a significant disconnect between organizational adoption of AI and the profound skepticism of young job candidates, who express deep concerns about fairness, transparency, and the potential for AI to perpetuate systemic discrimination.

This study shows the efficacy of leveraging transfer learning, specifically from residual networks, to detect CVDs and possible signs of CVDs. The findings indicate that leveraging transfer learning from residual networks alongside medical professionals is a highly promising approach for CVD detection and diagnosis, warranting further investigation.