让下一篇重要论文，不再错过。

原文摘要

A generated domain-specific program can be accepted by its host and still miss the reference construction. We measure the two events separately and test a short construction contract. The vehicle is Open Quantum Assembly Language (OpenQASM) 3. One 3-billion-parameter generator is run under seven conditions on 100 quantum approximate optimization (QAOA) and 100 variational quantum eigensolver (VQE) instances. Eighty of 100 QAOA signatures appear in some training split. Exact McNemar tests and 95% paired bootstrap intervals are used. The contract, a card, lists structural decisions, enters the prompt, and is checked without a simulator. Parse rates are 0.55 to 0.97 and full structural match is 0.02 to 0.87. On QAOA, at fixed weights, the card moves full match by +32.0 percentage points on card-trained weights (interval +22 to +42) and by -13.0 (-23 to -3) without that training. The +45.0-point difference is not a deployment contrast. The same-step plan-free gain is +23.0 (+13 to +33); the primary distributional score does not separate it. Against the earlier checkpoint the gain is +27.0 (+17 to +37), and the checkpoint also changes. A rule card is not separated from the learned planner, nor is a predicted-card compiler (0.760 vs. 0.780). On 20 QAOA rows outside every training split, the interval includes zero. Under this card, VQE adherence is 0.020 and full match stays near 0.03. Report the two checks separately. Insert a card only into a generator trained to read it, and only where a pilot shows adherence.