MOTIF

MOTIF — See How Ideas Connect Books unfold linearly, but meaning emerges through relationships across the text. MOTIF (Meaning-Oriented Text Interrelationship Framework) transforms books into interactive landscapes of ideas, revealing how concepts, events, and interpretations develop, connect, and change. Built for the Meta Global AI Developer Hackathon, MOTIF is powered by Meta's Muse Spark 1.3 and MORe (Meaning-Oriented Representation), an original experimental framework developed for this project. MORe processes books incrementally, passage by passage. It extracts evidence-grounded representations, connects new information with earlier memories, records changes in interpretation, and constructs higher-level meanings from multiple passages. Every connection remains traceable to the original text. MOTIF makes these representations accessible through two interactive views: - Journey of Ideas: A visual overview of how a book's ideas, arguments, and narrative develop, including returning threads that reveal reinterpretations and convergences that represent constructed meanings. - The Weave: A detailed representation of relationships, revisions, and textual evidence for deeper exploration. The prototype demonstrates this approach on three literary works, including H. G. Wells's complete *The Time Machine* (32,310 words), processed across 86 passages. MOTIF is designed around a process-once, explore-many-times architecture: developers or publishers preprocess books using MORe, and readers explore the stored representations without repeated AI inference. The long-term vision is to bring this capability into digital reading platforms, education, and humanities research, helping people understand not only what a book says, but how its meaning unfolds.