AI

Zugwise: Domain-Aware Game Reconstruction for Digitizing Handwritten Chess Scoresheets

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 13/11/2026, 07:48:24 UTC.

Briefings

Zugwise is a browser-based, offline game reconstruction system for digitizing handwritten chess scoresheets that identifies silent errors by treating the task as game reconstruction rather than simple recognition. It uses computer-chess machinery like quiescence search and static evaluation to detect illegal moves and trace their causes backward through the game. The system was tested on two tournament sections, reducing silent errors from 16 to 1 and from 50 to 13, while improving the top-rank rate of human-verified fixes from 58.8% to 78.0%. It offers a three-way adjudication protocol for domain records where no single record is ground truth.

Key points

• Zugwise repurposes computer-chess machinery to detect silent errors in handwritten chess scoresheets by treating the task as game reconstruction rather than simple recognition.
• The system reduces silent errors from 16 to 1 and from 50 to 13 in two tournament sections, improving the top-rank rate of human-verified fixes from 58.8% to 78.0%.

Context

This research addresses the limitations of standard handwriting-recognition approaches that miss errors yielding illegal moves versus those yielding legal-but-wrong moves. The system runs entirely in the browser and is free, private, and offline-capable, offering a three-way adjudication protocol for domain records where no single record is ground truth.

Limitations

The study covers only two tournament sections; the system does not establish which workflow is faster or more accurate. The evidence is preprint status (arXiv:2611.14544v1) and includes uncertainty regarding the exact causal claims and performance metrics across all sections.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 13/11/2026, 07:53:11 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeif6nh63gilpuh4rvnjo67ckk6dnlk3auk25d5us3u4td2ivc4cmla