Experiments

The Snapshot Bug and 1D Collapse Retraction

Retraction. , , and evolution loops reset hidden states to zero BEFORE saving snapshots. All hidden state analysis was on zero vectors. The "1D energy counter" finding was completely wrong.

Corrected data: effective rank 5.1-7.3 (not 1-3), energy $R^2$ = -3.6 to -4.6 (not 1.0), PC1 variance 25-38% (not 95-100%). Hidden states are moderately rich and do NOT encode energy linearly.

Lesson: When hidden states appear degenerate, first verify you're analyzing actual post-cycle states, not zeroed reset buffers.