diff --git a/docs/superpowers/specs/2026-05-01-sp5-magnitude-differentiation-and-eval-collapse-design.md b/docs/superpowers/specs/2026-05-01-sp5-magnitude-differentiation-and-eval-collapse-design.md
index f287ccd1d..a508549c7 100644
--- a/docs/superpowers/specs/2026-05-01-sp5-magnitude-differentiation-and-eval-collapse-design.md
+++ b/docs/superpowers/specs/2026-05-01-sp5-magnitude-differentiation-and-eval-collapse-design.md
@@ -138,17 +138,6 @@ Code audit of `experience_action_select`'s Thompson direction-branch sampling: u
 
 Documented here for completeness; the SP5 brainstorm flagged this as a question. Code inspection resolved it.
 
-### Layer A close-out: host-EMA → GPU sweep migration
-
-Migrate 5 remaining host-aggregated EMA sites to GPU per `feedback_no_cpu_compute_strict`:
-- `training_sharpe_ema` — requires per-step PnL aggregation on GPU
-- `max_dd_ema` — same
-- `gamma_blend` — host-aggregated eval result, port to GPU
-- `LearningHealth` composition pipeline — multi-step host arithmetic, port to GPU
-- `HealthEmaTrackers` — q_gap_ema + q_var_ema + grad_norm_ema host-side EMAs
-
-Substantial: requires per-step trade-PnL aggregation kernel + multi-step composition kernel. Estimated 600-1000 LOC for this layer alone.
-
 ## Architecture (mirror SP4 layer structure)
 
 ### Layer A — additive infrastructure