CiteSee has informed the design of numerous tools for augmenting scholarly reading experiences — cited as a representative approach for personalizing inline citation context based on reading history, for helping researchers prioritize and discover relevant literature, and for supporting sensemaking during literature reviews — while also serving as a reference point for work on contextual UI design patterns, AR-based paper reading systems that bridge physical and digital documents, reliable inline citation in language model outputs, and document augmentation pipelines, with its mixed-effects statistical modeling approach additionally adopted in several user study analyses.