mlsanityData to 7 Oct 2026

Capture-Quiet Decomposition: A Verification Theorem for Chess Endgame Tablebases

arXiv 2604.07907 ↗First posted 9 Apr 2026cs.AI cs.LOcited by 0

Not on the map. Why?

Abstract (arXiv)

We present the Capture-Quiet Decomposition (CQD), a structural theorem for verifying Win-Draw-Loss (WDL) labelings of chess endgame tablebases. The theorem decomposes every legal position into exactly one of three categories -- terminal, capture, or quiet -- and shows that a WDL labeling is correct if and only if: (1) terminal positions are labeled correctly, (2) capture positions are consistent with verified sub-models of smaller piece count, and (3) quiet positions satisfy retrograde consistency within the same endgame. The key insight is that capture positions anchor the labeling to externally verified sub-models, breaking the circularity that allows trivial fixpoints (such as the all-draw labeling) to satisfy self-consistency alone. We validate CQD exhaustively on all 35 three- and four-piece endgames (42 million positions), all 110 five-piece endgames, and all 372 six-piece endgames -- 517 endgames in total -- with the decomposed verifier producing identical violation counts to a full retrograde baseline in every case.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 1 of its 12 references that are in the map. First posted on arXiv 9 Apr 2026.

Builds on

1 of 12 references.

References · 1

  1. 2024Set-Based Retrograde Analysis: Precomputing the Solution to 24-card Bridge Double Dummy Dealscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents
  2. 2026Do Chess Explanations Reflect Model Decisions? Behavioral and Token-Level Tests of LLM Reasoning Faithfulness
  3. 2025Beyond Accuracy: A Geometric Stability Analysis of Large Language Models in Chess Evaluation
  4. 2025LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
  5. 2025ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
  6. 2025Tracking World States with Language Models: State-Based Evaluation Using Chess
  7. 2026ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics
  8. 2026How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess