diff --git a/crates/ml/src/trainers/dqn/fused_training.rs b/crates/ml/src/trainers/dqn/fused_training.rs
index 98e5c48c2..321ccca6d 100644
--- a/crates/ml/src/trainers/dqn/fused_training.rs
+++ b/crates/ml/src/trainers/dqn/fused_training.rs
@@ -1479,17 +1479,20 @@ impl FusedTrainingCtx {
         self.trainer.compute_predictive_coding_loss(self.batch_size)
             .map_err(|e| anyhow::anyhow!("Predictive coding (G12): {e}"))?;
 
-        // G6 + G10 forward-only (measurement). Both kernels are now graph-safe
-        // (G6: single-block direct overwrite; G10: per-sample → c51_loss_reduce).
-        // No backward yet — wired only to log the penalty magnitudes via
-        // HEALTH_DIAG. Decision on backward integration depends on whether
-        // the measured penalty is meaningfully larger than what existing
-        // mechanisms (spectral_norm for G10, NoisyNets/ensemble-KL for G6)
-        // already enforce. V7-gem methodology: measure before commit.
-        self.trainer.compute_branch_independence(self.batch_size)
-            .map_err(|e| anyhow::anyhow!("Branch independence (G6 measure): {e}"))?;
-        self.trainer.compute_temporal_consistency(self.batch_size)
-            .map_err(|e| anyhow::anyhow!("Temporal consistency (G10 measure): {e}"))?;
+        // G6 + G10 measurement (commit 61ab27ff3) found both penalties are
+        // dominated by existing mechanisms:
+        //   G10 temporal_consistency: 0.000000–0.000002 across 14 epochs.
+        //     Cosine similarity between consecutive h_s2 samples almost never
+        //     exceeds the 0.95 threshold; spectral_norm already enforces a
+        //     global Lipschitz constraint that subsumes per-pair Lipschitz.
+        //   G6 branch_independence: ~1e-4 (orders of magnitude smaller than G12).
+        //     NoisyNets injects different parameter noise per layer → the 4
+        //     advantage branches are already ~99.99% diverse without explicit
+        //     cosine-similarity penalty.
+        //
+        // Per V7-gem methodology: when the existing mechanisms cover the signal,
+        // wiring backward adds gradient noise without value. Both calls removed
+        // here; the kernels and Rust glue are deleted in a follow-up cleanup.
 
         // Ensemble diversity: heads 1..K-1 forward + KL gradient + trunk backward.
         // Runs inside aux_child graph — gradients land in grad_buf before Adam.
diff --git a/crates/ml/src/trainers/dqn/trainer/training_loop.rs b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
index 8e9c4f277..0ff8e8167 100644
--- a/crates/ml/src/trainers/dqn/trainer/training_loop.rs
+++ b/crates/ml/src/trainers/dqn/trainer/training_loop.rs
@@ -2148,16 +2148,16 @@ impl DQNTrainer {
             // diag = pure monitoring signals (not in reward): sharpe EMA (formerly w_dsr
             // reward input) and action entropy normalized to [0,1] (formerly
             // position_entropy_weight reward). See Phase 1 inventory better-form taxonomy.
-            // gems = G6/G10/G12 gem-penalty values (sync DtoH from GPU; once per epoch).
-            // V7 methodology: log first to measure whether the gem is doing real work
-            // before deciding to wire its backward gradient.
-            let (g6_loss, g10_loss, g12_loss) = if let Some(ref fused) = self.fused_ctx {
-                fused.read_gem_losses()
+            // gems = G12 predictive_coding loss (active in training). G6 + G10
+            // were measured (commit 61ab27ff3) and found redundant with existing
+            // mechanisms (NoisyNets, spectral_norm); their readbacks were removed.
+            let g12_loss = if let Some(ref fused) = self.fused_ctx {
+                fused.read_gem_losses().2  // (g6, g10, g12) — keep g12 only
             } else {
-                (0.0, 0.0, 0.0)
+                0.0
             };
             tracing::info!(
-                "HEALTH_DIAG[{}]: health={:.2} components [q_gap={:.2} q_var={:.2} atoms={:.2} grad_stable={:.2} ens_agree={:.2} grad_cos={:.2} spectral={:.2}] effective [cql_alpha={:.4} iqn_budget={:.2} cql_budget={:.2} c51_budget={:.2} tau={:.5} sarsa_tau={:.2} gamma={:.3} cf_ratio={:.2}] novels [distill={} barrier={:.3} plasticity={} ib={:.3} ensemble_collapse={:.2} contrarian={} meta_q_pred={:.2}] diag [sharpe_ema={:.3} action_entropy={:.2}] gems [g6_branch_indep={:.6} g10_temporal={:.6} g12_predictive={:.6}]",
+                "HEALTH_DIAG[{}]: health={:.2} components [q_gap={:.2} q_var={:.2} atoms={:.2} grad_stable={:.2} ens_agree={:.2} grad_cos={:.2} spectral={:.2}] effective [cql_alpha={:.4} iqn_budget={:.2} cql_budget={:.2} c51_budget={:.2} tau={:.5} sarsa_tau={:.2} gamma={:.3} cf_ratio={:.2}] novels [distill={} barrier={:.3} plasticity={} ib={:.3} ensemble_collapse={:.2} contrarian={} meta_q_pred={:.2}] diag [sharpe_ema={:.3} action_entropy={:.2}] gems [g12_predictive={:.4}]",
                 epoch,
                 health_value,
                 self.learning_health.components.q_gap_norm,
@@ -2184,8 +2184,6 @@ impl DQNTrainer {
                 self.last_meta_q_pred.unwrap_or(0.0),
                 self.training_sharpe_ema,
                 self.last_action_entropy.unwrap_or(1.0),
-                g6_loss,
-                g10_loss,
                 g12_loss,
             );