Paper

Elo-Disentangled Player-Style Embeddings for Human Chess via Rating-Conditioned Residual Move Model

Unreadunread

AI summary

arXiv:2606. 25176v1 Announce Type: new Abstract: We study representation learning for individual human chess style: a per-player embedding learned from a player's move history such that inner products measure stylistic similarity, while being approximately disentangled from playing strength (Elo).

Reading status

Priority

About this paper

Authors: Jason Carlson
Released: 2026-06-25 (14d ago)
Topic: Related to current project
Relation to my work: Read next because Elo-Disentangled Player-Style Embeddings for Human Chess via Rating-Conditioned Residual Move Model overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, strong, line, without, candidates, candidate, model. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2606.25176

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Elo-Disentangled Player-Style Embeddings for Human Chess via Rating-Conditioned Residual Move Model. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.