We are again seeking volunteers to solve our puzzles and help promote AI research to create chess study materials. Go to https://puzzles.knowledgepit.ai/ and follow the instructions. Your help is much appreciated! Read the previous blog post for details https://lichess.org/@/frugofruit90/blog/help-us-create-better-chess-puzzles/COqPCkMM
The AI competition for the best algorithm to predict chess puzzle difficulty (and the associated conference) is officially over. Congratulations to the winning teams!
Team “bread emoji” - Tyler Woodruff, Oleg Filatov, Marco Cognetta
Team “anansch” - Anan Schutt and Tobias Huber and Elisabeth Andre
Team “ousou” - Sebastian Bjorkqvist
Full results are available on the competition website https://knowledgepit.ml/predicting-chess-puzzle-difficulty/. Additionally, seven papers were written by the top teams and the competition organizers (including yours truly) and published as part of the IEEE 2024 Big Data Proceedings:
J. Zyśko, M. Świechowski, S. Stawicki, K. Jagieła, A. Janusz, and D. Ślęzak, “IEEE Big Data Cup 2024 Report: Predicting Chess Puzzle Difficulty at KnowledgePit.ai,” 2024.
T. Woodruff, O. Filatov, and M. Cognetta, “The bread emoji Team’s Submission to the IEEE BigData 2024 Cup: Predicting Chess Puzzle Difficulty Challenge,” 2024.
A. Schütt, T. Huber, and E. André, “Estimating Chess Puzzle Difficulty Without Past Game Records Using a Human Problem-Solving Inspired Neural Network Architecture,” 2024.
S. Björkqvist, “Estimating the Puzzlingness of Chess Puzzles,” 2024.
A. Rafaralahy, “Pairwise Learning to Rank for Chess Puzzle Difficulty Prediction,” 2024.
D. Ruta, M. Liu, and L. Cen, “Moves Based Prediction of Chess Puzzle Difficulty with Convolutional Neural Networks,” 2024.
S. Miłosz and P. Kapusta, “Predicting Chess Puzzle Difficulty with Transformers,” 2024.
The competition was a huge scientific success, with almost a hundred teams from all over the world participating. We couldn’t have done it without help from the Lichess team (special shoutout to Sol!). Moreover, we are super grateful for the work of hundreds of volunteers who tried their best at solving the puzzles themselves! Congratulations to the winners of the free coaching lottery:
1) Free lesson with 2240 FIDE peak Elo player (me): sorshf, rybiryj, meow, kvltvr_wvltvr, owenowen, jztrain, Stormcrow, Dusterini, MJT1980
2) Free lesson with GM Zbigniew Pakleza: GamePerFrame
All the winners were contacted by me on Lichess. I had a blast giving the free lessons and meeting so many wonderful people from around the world! <3
Because of big interest in the first edition, we are organizing a second one starting in January. It will feature a bigger, richer training dataset and a more accurate test set. AI researchers and practitioners - stay tuned for details at https://knowledgepit.ml/!
Since we are organizing the second edition of the competition, we are again gathering people’s puzzle attempts! We kindly ask everyone to log in at https://chess.knowledgepit.ai/ with your Lichess account (it’s easy, free and safe) and solve as many puzzles as you’d like!
Once again, big thank you to everyone who participated and see you in the second edition!
