experiments: freeze useful-depth BP screen

1 files changed, 16 insertions, 0 deletions

diff --git a/ROADMAP.md b/ROADMAP.md
index b4fa72b..308cce8 100644
--- a/ROADMAP.md
+++ b/ROADMAP.md
@@ -95,6 +95,22 @@ recover at least 70% of that paired gain; the strongest competing local rule mus
 than 50%, or SDIL must beat it by at least 2 points at the deep endpoint. Removing the final third
 of trained blocks must reduce SDIL performance, ruling out an effective shallow-network solution.
 
+The C2 candidate is frozen from scratch pilots before formal validation: a two-level Telgarsky
+tent-map binary task, one informative input, width 8, ReLU residual students, 80 epochs,
+batch size 256, `eta=0.03`, and momentum 0.9. Each task has 10,000 generated training examples,
+of which a stratified 2,000-example validation split (`split_seed=2027`) is held out; its untouched
+test set has 5,000 independently generated examples. Shallow/deep are fixed to d1/d4. A BP shape
+screen uses task seeds 0, 1, 2, student seed 0, and depths 1, 2, 3, 4, 6. Contextual depths cannot
+replace d4 after results are observed. The BP screen passes only if mean d1-to-d4 gain is at least
+5 points, every task seed gains, mean d4 final-third-lesion drop is at least 2 points, and every
+task seed is hurt by the lesion. Only final validation metrics are observed.
+
+If BP passes, the local-rule validation panel freezes d1/d4 for BP, FA, DFA, and no-traffic SDIL
+with C3's `K=1/every=4`, crossing the same three task seeds with student seeds 0--4. Its test panel
+may run only if the original C2 gate holds on validation and the d4 SDIL lesion loses at least
+2 points on average with at least 10 of 15 paired runs harmed. Test confirmation retrains on the
+same 8,000-example training subset and evaluates each task seed's untouched 5,000 examples once.
+
 ### C3. Causal calibration is genuinely amortized
 
 **Status: passed on 2026-07-22.** The frozen five-seed confirmation retained 112.9% of the K16/e4