This $195,000 Project Grant award from the National Science Foundation (NSF) Division of Behavioral and Cognitive Sciences (CFDA 47.075) supports the development of an open-source programming language called SweetPea. SweetPea is designed to automate the implementation and documentation of unbiased experimental designs, addressing key issues of transparency and replicability in empirical research.
The project, led by Princeton University, aims to expand SweetPea's core functionality to support various design strategies, automate the documentation process, and grow the user and contributor community. SweetPea provides an intuitive interface for expressing experimental designs and leverages advanced computational algorithms for sampling and analysis. This ensures experimental designs are properly implemented without introducing confounding factors. The project also uses large language models to robustly document experimental designs. These capabilities are expected to improve the accuracy, transparency, and replicability of experimental research across disciplines like psychology, neuroscience, behavioral economics, and machine learning.
Generated 5/14/24, 9:40 AM