experiments: freeze context-vectorizer C2 recovery

1 files changed, 15 insertions, 0 deletions

diff --git a/ROADMAP.md b/ROADMAP.md
index 702030a..7079f2d 100644
--- a/ROADMAP.md
+++ b/ROADMAP.md
@@ -125,6 +125,21 @@ fixed linear output-error vectorizer `A_l c` is now the leading limitation: incr
 directions/frequency or simple gain normalization did not stabilize scratch validation. No C2
 test panel may run unless a separately declared mechanism change passes validation.
 
+The mechanism-recovery candidate is a bounded context-conditioned vectorizer,
+`a_l = A_l c + G_l vec(c outer tanh(h_top))`, with both pathways calibrated by the same local
+node-perturbation regression. The gate term is zero-initialized and vanishes when `c=0`, preserving
+neutral-period innovation identification. An exploratory task-seed-0 validation budget compared
+linear, per-cell soma-gated, and context-gated forms; `eta_A in {0.005, 0.01, 0.02}`; and K1/e2,
+K1/e4, and K4/e4. Bounded context gating with `eta_A=0.01`, K1/e4 was selected by mean d4
+validation accuracy. It recovered 70.2% of BP's task-0 depth gain but retained one bad basin.
+
+Before any C2 test, an independent confirmation is frozen on new task seeds 3, 4, 5 and student
+seeds 0--4, crossing BP, FA, DFA, and context-SDIL at d1/d4 (120 validation-only runs). It uses the
+same original C2 thresholds, and additionally requires at least 10/15 context-SDIL depth gains to
+be positive; its d4 lesion must lose at least 2 points on average and harm at least 10/15 runs.
+Failure closes this recovery. Passing freezes a single test confirmation over task seeds 0--5,
+student seeds 0--4, all four methods, and d1/d4, retrained on the unchanged 8,000-example subsets.
+
 ### C3. Causal calibration is genuinely amortized
 
 **Status: passed on 2026-07-22.** The frozen five-seed confirmation retained 112.9% of the K16/e4