docs(ms-ai-architect): R11 §9.6 — trekker tilbake cond3-fellingen av idx 27; navngir scope-hoppet; presiserer at gaten er suiten [skip-docs]

To overpåstander i §9.6 rettet, begge funnet ved gjennomgang.

1. idx 27 ble skrevet som en cond3-FELLING. Den påstanden hvilte på to ledd
   som ikke bærer den:
   - Kilden fila siterer er en HUB. FAQ-en jeg grunnla på ligger én hop
     utenfor. Å telle en hubs barn som "kilden" er en NY lesning av hva
     grounding betyr — samme klasse som korpus-scope-spørsmålet §9.5
     bevisst lot stå uratifisert. Jeg utøvde den stille. Den er nå navngitt
     som åpent spørsmål.
   - "Makers CAN REQUIRE user confirmation" beskriver en KONFIGURERBAR
     kapabilitet, ikke noe kilden etablerer som til stede. Det er tynnere
     evidens enn "kilden etablerer mekanismen".

   Cond 3 står derfor fortsatt human_must_confirm. Denne økten hverken
   klarerte eller felte den.

   Utfallet er uendret: idx 27 forlater O2 uansett, fordi defekten er
   MODALITET (built-in vs maker-konfigurerbar) og riktig fiks derfor er en
   erstatning — utenfor delete-only-konvolutten uansett hvordan cond 3
   lander. Det er den bærende grunnen, og den er uavhengig av begge ledd
   over.

2. §8 presenterte check-g7-queue.mjs som håndhevings-mekanismen. Den har
   ingen runner og kjører kun når noen skriver kommandoen. Det bindende er
   testens siste case, som kjører den ekte køen mot live korpus hver
   suite-kjøring. Presisert begge steder.

Operatørutfallene fra økten også ført i §9.6 (idx 26 -> G7, form b, kolon-fiks).

Suite 1047/1047.

docs/r11-pilot-results.md

@@ -750,26 +750,44 @@ open condition, it **concentrates it**: after reduction, 100 % of the edit is th
 part nobody had cleared. The original two-row form had a clean half; the reduced
 form has none. "One condition remains" understated it.
 
-**idx 27 — FAILED, and the checker may say so unilaterally.** The file cites
-`microsoft-copilot-studio/responsible-ai-overview` for the whole section. That page
-is a hub; it establishes nothing itself, but it links the FAQ set, and
-`faqs-generative-orchestration` states plainly:
+**idx 27 — leaves O2, on modality grounds. Cond 3 is NOT settled, and the scope
+question underneath it is named rather than assumed.**
+
+The file cites `microsoft-copilot-studio/responsible-ai-overview` for the whole
+section. That page is a **hub**: it establishes nothing itself, it links the FAQ
+set. One hop out, `faqs-generative-orchestration` says:
 
 > "Makers can require user confirmation before executing tools that modify data."
 
-The source therefore **does** establish a confirmation mechanism for Copilot Studio.
-Cond 3 asks whether the subtraction destroys source-confirmed information, and the
-answer is yes — so **cond 3 fails and idx 27 leaves O2 entirely.** This is a kill,
-not a clearance, so §9.3's asymmetry rule permits it without a ratifier.
+**Two cautions, both against the stronger reading this section originally carried.**
 
-The row is not fabricated; its **modality** is wrong. The file asserts confirmation
-prompts as a *built-in disclosure*, whereas the source makes them a maker-configured
-option. The correct repair is a replacement, not a deletion — which is an O3-class
-fix, outside the delete-only envelope. Same for the Chat-interface row the reduction
-kept: the FAQ documents a default transparency **message** ("Just so you are aware,
-I sometimes use AI to answer your questions."), not the "Powered by AI" **badge** the
-file claims. That row is not in this subtraction, but it is now on the record as
-imprecise.
+*First, a scope decision, not a free move.* Grounding on a page the file does not
+cite — reached one hop through the cited hub — is a **new reading of "the source"**,
+structurally the same kind of expansion as the corpus-scope reading of cond 2 that
+§9.5 deliberately left unratified. R11 has otherwise held grounding to the cited
+URL throughout. **Whether a hub's linked children count as the cited source is
+therefore UNRATIFIED**, and is recorded here as an open question rather than
+exercised silently.
+
+*Second, the quote is thinner than it looks.* "Makers **can require**" describes a
+**configurable capability**, not a feature the source establishes as present. Cond 3
+asks whether the subtraction destroys what the source establishes; an option a maker
+may enable is weak evidence for that. So **cond 3 stands unresolved at
+`human_must_confirm`** — this pass did not clear it and does not claim to have
+failed it either.
+
+**idx 27 leaves O2 anyway, and for a reason that does not depend on either point
+above.** The defect is **modality**, not fabrication: the file asserts confirmation
+prompts as a *built-in disclosure*, whereas the mechanism — on any reading of the
+evidence — is maker-configured. Deleting the row would remove a claim whose core is
+sound and whose framing is wrong. **The correct repair is a replacement, and
+replacement is outside the delete-only envelope by definition.** That holds whether
+cond 3 eventually fails or clears, which is why it is the load-bearing reason.
+
+Same for the Chat-interface row the reduction kept: the FAQ documents a default
+transparency **message** ("Just so you are aware, I sometimes use AI to answer your
+questions."), not the "Powered by AI" **badge** the file claims. Not part of this
+subtraction, but now on the record as imprecise.
 
 **idx 26 — confirmed, and its held-back half is now positively false.** The canonical
 scorecard segments, from `how-to-responsible-ai-scorecard`, are: summary/model
@@ -836,6 +854,14 @@ measurement (b) is the better fit, and (a) would be mis-sized against the eviden
 **Verified score is unchanged at 4 of 46.** idx 27 leaves O2 without becoming a
 subtraction; idx 26 remains available to a ratifier as a two-part accept.
 
+**Operator resolution, same session.** idx 26: the partial fix was **declined** —
+a delete-only edit that knowingly leaves a measured-false claim standing while
+introducing a renumbering artifact buys too little, so the whole 117+300 pair went
+to G7. G7 form: **(b), the named queue**, on the measurement above. The idx 17
+regression was fixed by changing the colon to a period, making the lead-in a
+complete and independently true sentence that the `**Verified**` stamp correctly
+covers; the corpus was swept for the same defect shape with no other occurrence.
+
 ## Appendix A — the 15 admitted proposals, hand-verified
 
 Every proposal the classifier (§4 + context condition) admitted over the whole