docs(PENDING-181): the jurist's two notes answered

(1) The canary's blockers, checked: REVIEWED-123 freezes reference-verification-
ladder.md as a DOCUMENT and says nothing about building instruments, so the
freeze is incidental. The real gate is PENDING-139 — and the canary is not a new
instrument at all, it IS that item's unruled option (b). Today's instance 6 also
discriminates between its options, which nothing in the item previously did:
option (a)'s widened ^#{2,4} still fails on an indented heading, so (a) would not
have caught it, and (b) catches it only if its residual scan is anchorless.

(2) The three-mechanisms finding lifted out of the addenda into a cost clause the
ruling can reach: two mechanisms are catchable by steward attention and one is
not, so the remedy is not justified by clerical load alone.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01T1i5VRfHjD79hfaXjWsBXA

PENDING.md

@@ -4556,3 +4556,40 @@ carries its own open item (PENDING-139). Named so the next hand does not have to
 by having a ruling go missing.
 
 **Awaiting:** unchanged — steward authorization on the parent proposal.
+
+**JURIST'S TWO NOTES, ANSWERED. 2026-09-10.**
+
+**(1) Which blocker is load-bearing — and the answer is NEITHER, because the canary is
+not a new instrument.** Checked rather than assumed:
+
+- **REVIEWED-123 condition 1 freezes a DOCUMENT**, in its own words: *"no additions,
+  rewordings, removals or reorderings of `reference-verification-ladder.md`."* It says
+  nothing about building instruments. **The freeze blocks promoting the lesson; it does
+  not block the check.** Incidental, as the jurist suspected.
+- **The real gate is PENDING-139, and it is nearer than "blocked": the canary IS that
+  item's option (b)** — *"emit a count of amendment-like headings the parser could not
+  classify, so a future unmatched form announces itself instead of vanishing."* That is
+  the invariant, already drafted, already under an unruled options set.
+
+⚠ **AND TODAY'S INSTANCE 6 DISCRIMINATES BETWEEN ITS OPTIONS, which no evidence in the
+item previously did.** PENDING-139's option (a) widens `RE_HEAD` to `^#{2,4}\s+REVIEWED-…`.
+**An indented heading still fails `^#`, so (a) would not have caught instance 6.** Option
+(b) catches it **only if its residual scan is anchorless** — otherwise the count of
+"headings the parser could not classify" inherits the identical blind spot and reports
+zero. **So instance 6 is evidence for (b) over (a), and a constraint on how (b) is
+written.** Recorded here rather than appended to PENDING-139, which is not this item.
+
+**(2) FOR THE RULING'S COST CLAUSE — carried out of the addenda deliberately, per the
+jurist's note that a ruling might not reach them.**
+
+> **The proposal's cost argument does not rest on clerical load alone.** Of the three
+> transit mechanisms recorded here, **two are catchable by a sufficiently attentive
+> steward and one is not**: leading indentation renders correctly, removes nothing, and
+> is invisible to every id-keyed reader while looking right to every human one. **For
+> that mechanism, no amount of steward attention is sufficient — the failure is not a
+> lapse of care and cannot be remedied by more of it.** A remedy justified only by
+> clerical burden would be optional; a remedy justified by a class of corruption that
+> attention cannot reach is not. **This is a structural reason, arriving after the
+> proposal was drafted, and it strengthens the argument the proposal makes from a single
+> 09-01 instance.**
+