schema: cognia-cdct-levelized-preregistration/1
frozen-before-results: true
seeds: 11,23,37,41,53,67,79,83,97,101
hypothesis: H3
claim: an exact declared loopback retains a binary state for 1000 ticks better than trained GRU and LSTM controls
training: 64 sequences x 32 ticks; identical set/reset/hold observations; 400 full-batch AdamW steps; lr 0.05
test: balanced set/reset cues followed by 999 hold ticks
primary-metric: final-tick accuracy
decision: SUPPORTED only when lower 95% Student interval of Levelized CDCT exceeds upper intervals of both controls
null-result: overlapping intervals
falsification: either control interval overlaps or exceeds the Levelized CDCT interval
