The bread emoji Team's Submission to the IEEE BigData 2024 Cup: Predicting Chess Puzzle Difficulty Challenge

Tyler Woodruff, Oleg Filatov, Marco Cognetta

Abstract: We detail the bread emoji team’s submission to the IEEE BigData 2024 Predicting Chess Puzzle Difficulty Challenge. Our solution revolved around the use of ensembled, pretrained, neural chessboard embedders (specifically, truncated Maia and Leela models) and an empirically-guided distribution rescaling postprocessing step.Our approach was the outright winner of the competition with a >16.4% reduction in mean squared error (MSE) over second place in the preliminary evaluation and a >13.3% reduction in MSE over second place in the final evaluation.1