AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess

Reid McIlroy-Young, Russell Wang, Siddhartha Sen, Jon Kleinberg, Ashton Anderson

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Prototype and concept dictionary models · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the transformer-based behavioral stylometry model instead of the opening baselineLichess players with 10K+ games, unseen targets, k=15 · 10K+ Lichess, candidate pool 2844P@1: 0.244 -> 0.860Improved
Include opening moves at inference (k=0) rather than excluding them (k=15)Behavioral stylometry model · 10K+ Lichess, unseen targets, candidate pool 2844P@1: 0.860 -> 0.979Improved
Replace the personalized move-matching approach with the shared behavioral stylometry modelMcIlroy-Young et al. task · 400-player candidate pool, k=15P@1: 0.552 -> 0.953Improved
Apply the amateur-trained model to high-ranked playersBehavioral stylometry model · High-ranked unseen players, candidate pool 2157, k=15P@1: 0.039 -> 0.308Improved
Add Lichess amateurs to the candidate pool of high-ranked playersBehavioral stylometry model · High-ranked unseen players, k=15P@1: 0.308 -> 0.301No clear effect
Use the transformer instead of an LSTM to aggregate move features (ablation)Behavioral stylometry model · 10K--40K+ Lichess unseen, k=15, candidate pool 2844P@1: 0.7803 -> 0.8599Improved
Use all moves instead of a five-move opening window (ablation)Opening baseline · 10K+ Lichess unseen, k=15P@1: 0.234 -> 0.277Improved
Train with 32-move windows instead of 10-move windows (ablation)Behavioral stylometry model · Training validation lossvalidation lossImproved
Train only on windows starting at move 15 or later (ablation)Behavioral stylometry model · Candidate pool and evaluation pool of 232 playersaccuracy: 0.9927 -> 0.390Hurt
Replace the 512-dimensional embedding with a 128-dimensional embedding (ablation)Behavioral stylometry model · Training validation lossvalidation lossHurt
Replace GE2E loss with ArcFace (ablation)Behavioral stylometry model · Evaluated settingsconvergenceHurt
Train on only 400 players rather than the full training population (ablation)Behavioral stylometry model · McIlroy-Young et al. task, k=15P@1: 0.953 -> 0.825Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy