diff --git a/specs/InnerLoop.md b/specs/InnerLoop.md
index de5d34f..e0df11d 100644
--- a/specs/InnerLoop.md
+++ b/specs/InnerLoop.md
@@ -106,11 +106,40 @@ evidence verdict for those rows caps at `parity`, never `better`.
 ### Step 2 — Approve (adversarial review)
 
 For tier-L passes, approval is earned through an **adversarial review**: a
-separate session (or agent), given only the survey document, attempts to
-break it — an omitted candidate, a stale or unverifiable benchmark, an
-unmeasured claim presented as measured. Exactly **one round**: challenge,
-then response. The survey is approvable only when every challenge is either
-answered with evidence or conceded and folded into the survey.
+separate session (or agent) attempts to break the work. Exactly **one
+round**: challenge, then response. The work is approvable only when every
+challenge is either answered with evidence or conceded and folded in.
+
+**The review target follows the risk.** Reviewing the survey was the
+original rule, and it is the wrong target for a capability whose claim
+rests on numbers — every serious error in this project has been in
+measurement or build configuration, not in prose.
+
+| the claim rests on | the reviewer is given | and must attempt |
+|---|---|---|
+| a survey of candidates | the survey | an omitted candidate; a stale or unverifiable benchmark; an unmeasured claim presented as measured |
+| **numbers** | the survey **and the harness and the evidence file** | **reproduce the number independently**; state what the harness would report if the work silently stopped |
+
+**What review cannot do — state this, do not discover it.** A reviewer
+re-derives the author's claims and therefore inherits the author's
+sampling. So:
+
+> **The reviewer re-derives on a different sample than the author used.**
+> Where only one sample exists, the review says so rather than reporting a
+> clean verify.
+
+*(v1.1, from CB-WP-0002: the dedup invariant was verified on the main
+transcript by the survey — 206/206 groups — and independently re-verified
+by the reviewer, who used the same transcript. It is false in the
+8-response `subagents/` tree neither examined. Two independent checks,
+one blind spot, because both sampled the same way. Only an assertion
+running over all the data at execution time caught it.)*
+
+**What review demonstrably does do.** Measured across two passes:
+**$0.66** and **$1.11**, roughly 1% of each pass, each finding
+approval-blocking defects — in CB-WP-0002 a target that would have made
+the evidence file certify a broken collector. The step pays for itself by
+a wide margin and the cost is not a reason to skip it.
 
 **Documentation requirement:** the research process, the challenge, and the
 resulting improvements to the research are each documented in timestamped
diff --git a/workplans/CB-WP-0003-loop-hardening.md b/workplans/CB-WP-0003-loop-hardening.md
index a4ac8c8..bdb52f1 100644
--- a/workplans/CB-WP-0003-loop-hardening.md
+++ b/workplans/CB-WP-0003-loop-hardening.md
@@ -124,7 +124,7 @@ dedup.
 
 ```task
 id: CB-WP-0003-T03
-status: todo
+status: done
 priority: medium
 state_hub_task_id: "1365b35d-4539-489a-beff-c072221e4702"
 ```