diff --git a/crates/ml-alpha/cuda/rl_ppo_clip_controller.cu b/crates/ml-alpha/cuda/rl_ppo_clip_controller.cu
index 97416164b..9422691d0 100644
--- a/crates/ml-alpha/cuda/rl_ppo_clip_controller.cu
+++ b/crates/ml-alpha/cuda/rl_ppo_clip_controller.cu
@@ -83,6 +83,16 @@ extern "C" __global__ void rl_ppo_clip_controller(
     float       eps_target = eps_prev * ratio;
     eps_target = fmaxf(EPS_MIN, fminf(eps_target, EPS_MAX));
 
+    // First-observation replace-directly per
+    // `pearl_first_observation_bootstrap`. See rl_target_tau_controller
+    // for the rationale — the Wiener blend's bootstrap contamination
+    // is what produced the step-7 l_v=249,782 spike in alpha-rl-qzstj
+    // (R9 audit 2026-05-23).
+    if (eps_prev == EPS_BOOTSTRAP) {
+        isv[RL_PPO_CLIP_INDEX] = eps_target;
+        return;
+    }
+
     // Wiener-α blend with floor per pearl_wiener_alpha_floor_for_nonstationary.
     const float a       = fmaxf(alpha, WIENER_ALPHA_FLOOR);
     float       eps_new = (1.0f - a) * eps_prev + a * eps_target;
diff --git a/crates/ml-alpha/cuda/rl_reward_scale_controller.cu b/crates/ml-alpha/cuda/rl_reward_scale_controller.cu
index dea590886..728cebceb 100644
--- a/crates/ml-alpha/cuda/rl_reward_scale_controller.cu
+++ b/crates/ml-alpha/cuda/rl_reward_scale_controller.cu
@@ -107,6 +107,19 @@ extern "C" __global__ void rl_reward_scale_controller(
     float       target = 1.0f / denom;
     target = fmaxf(REWARD_SCALE_MIN, fminf(target, REWARD_SCALE_MAX));
 
+    // First-observation replace-directly per
+    // `pearl_first_observation_bootstrap`. This is the load-bearing
+    // fix for the step-7 contamination cascade in alpha-rl-qzstj
+    // (R9 audit 2026-05-23): with prev=1.0 (bootstrap) and target=
+    // 1/832=0.0012, the Wiener blend at α=0.4 produced scale=0.600
+    // — applying 0.6 × $832 = $499 to V regression → MSE = 249,000.
+    // Replace-directly: scale = 0.0012 immediately → V target = 1.0,
+    // MSE = 1.0. Three orders of magnitude reduction.
+    if (prev == REWARD_SCALE_BOOTSTRAP) {
+        isv[RL_REWARD_SCALE_INDEX] = target;
+        return;
+    }
+
     // Wiener-α blend with floor per pearl_wiener_alpha_floor_for_nonstationary.
     const float a   = fmaxf(alpha_step, WIENER_ALPHA_FLOOR);
     float       out = (1.0f - a) * prev + a * target;
diff --git a/crates/ml-alpha/cuda/rl_rollout_steps_controller.cu b/crates/ml-alpha/cuda/rl_rollout_steps_controller.cu
index 334fb5dcf..2dd9cf5d3 100644
--- a/crates/ml-alpha/cuda/rl_rollout_steps_controller.cu
+++ b/crates/ml-alpha/cuda/rl_rollout_steps_controller.cu
@@ -92,6 +92,13 @@ extern "C" __global__ void rl_rollout_steps_controller(
     float       target    = prev * scale;
     target = fmaxf(ROLLOUT_MIN, fminf(target, ROLLOUT_MAX));
 
+    // First-observation replace-directly per
+    // `pearl_first_observation_bootstrap`.
+    if (prev == ROLLOUT_BOOTSTRAP) {
+        isv[RL_N_ROLLOUT_STEPS_INDEX] = target;
+        return;
+    }
+
     // Wiener-α blend with floor per pearl_wiener_alpha_floor_for_nonstationary.
     const float a   = fmaxf(alpha, WIENER_ALPHA_FLOOR);
     float       out = (1.0f - a) * prev + a * target;
diff --git a/crates/ml-alpha/cuda/rl_target_tau_controller.cu b/crates/ml-alpha/cuda/rl_target_tau_controller.cu
index c959e8d70..680dc0c88 100644
--- a/crates/ml-alpha/cuda/rl_target_tau_controller.cu
+++ b/crates/ml-alpha/cuda/rl_target_tau_controller.cu
@@ -85,6 +85,20 @@ extern "C" __global__ void rl_target_tau_controller(
     float       tau_target = tau_prev * ratio;
     tau_target = fmaxf(TAU_MIN, fminf(tau_target, TAU_MAX));
 
+    // First-observation replace-directly (R9 audit 2026-05-23): if
+    // prev is still exactly the hardcoded bootstrap value, this is
+    // the FIRST per-step fire that has real input signal. Per
+    // `pearl_first_observation_bootstrap`, "first observation
+    // replaces directly" — the Wiener blend `(1-α)·bootstrap +
+    // α·target` would leave 60% bootstrap contamination, distorting
+    // the controller's first emit. Write target directly instead.
+    // Subsequent steps (where prev has drifted off bootstrap via
+    // earlier blends) take the Wiener path below.
+    if (tau_prev == TAU_BOOTSTRAP) {
+        isv[RL_TARGET_TAU_INDEX] = tau_target;
+        return;
+    }
+
     // Wiener-α blend with floor per pearl_wiener_alpha_floor_for_nonstationary.
     const float a       = fmaxf(alpha, WIENER_ALPHA_FLOOR);
     float       tau_new = (1.0f - a) * tau_prev + a * tau_target;