NODES AI 2026: Graph Theory and Games: A Case Study on New York Times Connections

This talk features Shafik Quoraishee at NODES AI, focusing on "Graph Theory and Games: A Case Study on New York Times Connections". It explores how graph structures can enhance machine-assisted puzzle-solving in the New York Times Connections game, illustrating how puzzle elements, word relationships, and category patterns can be modeled in Neo4j. The speaker discusses the creation of a Neo4j-backed workflow for clustering, semantic grouping, and NLP-driven similarity scoring, emphasizing the use of embeddings, word associations, and candidate categories as nodes and relationships. The session highlights how graph algorithms and Cypher queries guide solver decisions, estimate puzzle complexity, and analyze player interpretation of categories and word relationships.