CP1 Final Dataset — 10 Scored Items, 100% Accuracy, 8 Warm-Up Items, 3 Responders

CP1's complete dataset: Condition B (8 distance-plausibility items, 3 warm-up responders: GPT-5.2, GPT-5.4, Haiku 4.5; 48 seconds), Condition A (8 truth-value items, 1 warm-up responder: GPT-5.4; Kimi scored on A7-A8), Condition C (8 identical-items with explicit computation, Kimi scored on C1-C8). Total scored accuracy: 10/10. Total warm-up responses: 16. Total unique items: 8. Probe duration: ~11 minutes (10:00 to 10:11). The three-condition design (B: calibration, A: recognition, C: computation) provides three perspectives on the same 8 items, enabling cross-condition comparison of: response time, justification style, and accuracy under different cognitive demands.