diff --git a/crates/ml-alpha/cuda/smoothness_lambda_controller.cu b/crates/ml-alpha/cuda/smoothness_lambda_controller.cu
index 0a58e75a2..1ebb41065 100644
--- a/crates/ml-alpha/cuda/smoothness_lambda_controller.cu
+++ b/crates/ml-alpha/cuda/smoothness_lambda_controller.cu
@@ -4,7 +4,7 @@
 // Reads `raw_per_h[5]` (emitted by output_smoothness_loss_and_grad),
 // maintains a per-horizon Wiener-α-floor EMA of observed jitter,
 // derives per-horizon target by anchoring on observed h30 jitter
-// scaled by HORIZONS[0]/HORIZONS[h], and emits next-step λ[h] with a
+// scaled by sqrt(HORIZONS[0]/HORIZONS[h]), and emits next-step λ[h] with a
 // permanent floor.
 //
 // Per `pearl_controller_anchors_isv_driven`: target is signal-derived,
@@ -33,14 +33,21 @@
 #define SLC_ALPHA_FLOOR  0.5f
 
 // HORIZONS = {30, 100, 300, 1000, 6000}.
-// Ratios HORIZONS[0]/HORIZONS[h] = {1, 0.3, 0.1, 0.03, 0.005}.
-// Constant array known at compile time.
+// Target ratio sqrt(HORIZONS[0]/HORIZONS[h]) = {1, 0.5477, 0.3162, 0.1732, 0.0707}.
+//
+// Rationale (2026-05-21 local-smoke trace finding): the linear ratio
+// {1, 0.3, 0.1, 0.03, 0.005} gave h6000 a 200x stronger target-undershoot
+// signal than h30, causing the controller to bombard h6000 with smoothness
+// gradient while h30 saw little. At base_lambda=0.1 local smoke this
+// collapsed h6000 val_auc to 0.514 (near-random) while middle horizons
+// improved. Square-root scaling caps the differential at ~14x, preserving
+// h6000 predictive capacity while still pushing toward slower change.
 __device__ __constant__ float TARGET_K_RATIO[SLC_N_HORIZONS] = {
-    1.0f,
-    30.0f / 100.0f,
-    30.0f / 300.0f,
-    30.0f / 1000.0f,
-    30.0f / 6000.0f,
+    1.0f,         // sqrt(30/30)   = 1.0
+    0.5477226f,   // sqrt(30/100)
+    0.3162278f,   // sqrt(30/300)
+    0.1732051f,   // sqrt(30/1000)
+    0.0707107f,   // sqrt(30/6000)
 };
 
 extern "C" __global__ void smoothness_lambda_controller(