diff --git a/crates/ml-alpha/src/trainer/integrated.rs b/crates/ml-alpha/src/trainer/integrated.rs
index 15a3341e2..31ea1bac3 100644
--- a/crates/ml-alpha/src/trainer/integrated.rs
+++ b/crates/ml-alpha/src/trainer/integrated.rs
@@ -8631,6 +8631,24 @@ impl IntegratedTrainer {
         self.dqn_head
             .forward(h_t_borrow, b_size, &mut self.q_logits_d)
             .context("step_with_lobsim_gpu: dqn_head.forward(h_t)")?;
+        // B-10 G1 (2026-06-01): Q-distribution informativeness diagnostic
+        // on online Q logits — emits ISV slots 730/731/732. Pure
+        // observability; reads q_logits_d immediately after the forward,
+        // before any downstream consumer (distill / Thompson / PPO).
+        // (Sister-launch added at line 6622 in `step_with_lobsim` — the
+        // GPU path here is the canonical one that the alpha_rl_train
+        // example actually exercises.)
+        self.dqn_head
+            .launch_q_distribution_stats(
+                &self.isv_dev_ptr,
+                &self.q_logits_d,
+                &self.atom_supports_d,
+                b_size,
+                &mut self.q_dist_entropy_pb_d,
+                &mut self.q_dist_range_pb_d,
+                &mut self.q_dist_abs_max_pb_d,
+            )
+            .context("step_with_lobsim_gpu: dqn_head.launch_q_distribution_stats")?;
         self.dqn_head
             .forward_target(h_t_borrow, b_size, &mut self.q_logits_target_st_d)
             .context("step_with_lobsim_gpu: dqn_head.forward_target(h_t) for distillation")?;