GraphIDyOM: A graph-native Python reimplementation of IDyOM for musical expectation modelling
Making a music prediction model easier to use and understand
A researcher rebuilt a widely-used model that predicts what note comes next in music, translating it from an outdated programming language into modern Python. The new version exposes how the model stores and retrieves memories, making it possible to inspect, visualize, and modify the internal workings that drive its predictions.
IDyOM is the standard tool for testing theories about how humans anticipate music, but its technical barriers meant most researchers couldn't easily modify or integrate it into their own work. GraphIDyOM removes those barriers, potentially accelerating research into musical cognition, improving music recommendation systems, and enabling new interactive applications that respond to listener expectations in real time.