A common way for chess players to practice tactical awareness is to solve chess puzzles, consisting of an initial position and a sequence of moves to achieve a winning position.This practice is more effective when puzzles are matched to the player's skill level.In this work, we present an approach for estimating the difficulty of a chess puzzle using only the initial position and the sequence of correct moves.Our approach uses a fine-tuned modification of the Maia-2 model combined with a set of hand-crafted features and features extracted from chess engines such as Leela Chess Zero and Stockfish.All of these features are then used as input to a gradient boosted decision tree model that predicts the final rating of the puzzle.We applied our approach to the FedCSIS 2025 Challenge on Predicting Chess Puzzle Difficulty Part 2, where it achieved first place.

Solving chess puzzles, which require finding a certain sequence of moves to achieve a winning position (such as checkmate or a significant material advantage), is a commonly used method for improving chess skills, particularly tactical awareness. Estimating the puzzlingness—i.e., the difficulty—of a chess puzzle is challenging and typically involves showing the puzzle to multiple players and measuring their success rate. In this work, we present a method for predicting the difficulty of chess puzzles using only the initial position and the sequence of correct moves. We generate multiple features, including both hand-crafted features and those extracted from chess engines such as Maia, Leela Chess Zero, and Stockfish. We also train a residual neural network to directly predict the Glicko-2 puzzle rating. The output of this neural network, along with the other generated features, serves as input to a gradient boosting decision tree model to predict the final Glicko-2 rating. Our model was applied to the IEEE BigData 2024 Cup competition on Predicting Chess Puzzle Difficulty, where it achieved third place.

Searching for novelty-destroying prior art is an important part of patent application drafting and invalidation. The task is challenging due to the detailed information needed to determine whether a document is novelty-destroying or simply closely related, resulting in the original search results not always being fully on target. Allowing the user to provide feedback on the relevance of the initial search results and iterating on the search may thus improve the results significantly. We present a relevance feedback method based on computing the affine vector subspace spanned by the relevant document vectors. The method can be used with any dense retrieval system, and we demonstrate its effectiveness in improving recall in prior art searches. We compare the subspace-based method to the Rocchio algorithm and show that the method is less sensitive to changes in hyperparameters when the number of relevant documents increases.

Performing prior art searches is an essential step in both patent drafting and invalidation. The task is challenging due to the large number of existing patent documents and the domain knowledge required to analyze the documents. We present a graph-based patent search engine that tries to mimic the work done by a professional patent examiner. Each patent document is converted to a graph that describes the parts of the invention and the relations between the parts. The search engine is powered by a graph neural network that learns to find prior art by using novelty citation data from patent office search reports where citations are compiled by human patent examiners. We show that a graph-based approach is an efficient way to perform searches on technical documents and demonstrate it in the context of patent searching.