9 it works for pairwise idea comparisons, but not for pools of 100 ideas. Lastly, they can be influenced by other factors such as sentence structure and length that are not easy to control for. An example of a pairwise comparison using cosine similarity can be found in Table 1. In our experiments, we generally considered a similarity above 0.8 as an identical idea which was established by testing. Appendix C shows additional examples of cosine similarity for ideas. Idea A Idea B Similarity QuickHeat Mug: An insulated, battery- powered coffee mug that can heat beverages within minutes and maintain the temperature. Ideal for students who need a warm drink during long study sessions but don't have immediate access to a kitchen. StudyBuddy Lamp: A compact, portable LED desk lamp with built-in timers for the Pomodoro study technique, adjustable brightness levels, and a USB charging port for smartphones. It's designed to help students focus and manage their study time effectively. 0.36 MiniMend Sewing Kit: A compact, travel- sized sewing kit with pre-threaded needles, buttons, and safety pins designed for quick fixes on-the-go, perfect for minor repairs or emergency adjustments to clothing. QuickFix Clothing Repair Kit: A compact kit with needles, thread, buttons, and fabric adhesive, designed for quick clothing repairs. Ideal for students who may not have the time or skills to sew but need to fix simple clothing mishaps. 0.82 Table 1: Cosine similarity example showing pairwise similarity between ideas A and B Number of Unique Ideas We also evaluate the number of unique ideas that can be generated with a given strategy. Consider generating ideas in a specific domain and assume there exists a finite (though large) number of ideas. As you pick random locations in this idea space, initially, chances are that they are very different from each other. Thus, their similarity is low. However, after a certain number of ideas generated, the likelihood of repetition increases. As we keep on “fishing in the pond” the number of unique “fish” to be caught is decreasing. In other words, if we throw the fish back into the pond after it is caught, the likelihood of catching a fish for the second time increases. We can use the information about how many ideas we have generated in total and how many of those are unique, i.e., have a cosine similarity less than 0.8 to all other previous ideas, to