fix(ms-ai-architect): idx-26f dialekt-retting — reparasjonen feilet paa sin egen begrunnende akse

Punkt 2 landet som 'fairness-target values', et hybridkompositum som er hverken
norsk eller engelsk, der punkt 1 gjengir samme kildebegrep som 'target-verdiene'.
Dialekt-konsistens var HELE argumentet for aa velge omskriving framfor sletting,
saa reparasjonen feilet paa aksen den ble begrunnet med. Rettet til
'fairness-maalverdiene'.

Koherens-gjennomlesingen etter foerste edit sjekket innholds-samsvar og slapp den
gjennom - den sjekket ikke kompositum-former. En koherens-sjekk arver aksen du
hadde i tankene da du skrev den.

Ratifiseringen laa i LABELEN ('kildens ordlyd i idx-26d-dialekten'); previewet bar
den defekte formen. Labelen er det ratifiserte objektet, saa rettingen krevde ingen
re-ratifisering - men et preview som gjengir labelen feil er en levende maate aa
smugle en uratifisert form forbi en operatoer som leser previewet.

I tillegg: idx-26f-resolutionen skiller naa eksplisitt mellom punkt 2/5 (re-verifisert
denne oekten) og punkt 1/3/6/7 (verifisert under idx-26d samme dag, arvet - ikke
re-kjoert her).

Suite 1047/1047.

docs/r11-pilot-results.md

@@ -1172,11 +1172,32 @@ documents catching.
 Cross-file grep before editing put all three replaced strings at zero occurrences
 elsewhere in the corpus.
 
+**The repair failed on its own justifying axis, and the coherence check passed it.**
+Item 2 first landed as `fairness-target values` — a hybrid compound that is neither
+language, where item 1 renders the same source concept as `target-verdiene`. Dialect
+consistency was the entire argument for choosing rewrite over deletion, so this is the
+repair failing the axis it was justified by. The whole-list re-read after the edit
+checked *content* alignment and passed; it did not check compound forms. **A coherence
+check inherits the axis you had in mind when you wrote it** — the same blind spot as a
+string invariant, one level up. Corrected to `fairness-målverdiene`.
+
+Note where the ratification sat: the operator approved the label *"kildens ordlyd i
+idx-26d-dialekten"*, while the illustrative preview carried the defective form. The
+label is the ratified object, so correcting toward it needed no re-ratification — but
+a preview that renders the label wrongly is a live way to smuggle an unratified form
+past an operator who is reading the preview.
+
 **The transferable part: the cheapest true edit is rarely the smallest diff.** A repair
 scoped to exactly the words an entry names will silently adopt whatever unmeasured
 content sits beside them — and adoption under a verification stamp is indistinguishable,
 to a reader, from verification.
 
+**One provenance seam left explicit rather than smoothed over.** The stamp's coverage
+after this closure rests on two different acts: items 2 and 5 were re-verified against
+the live source *this* session, items 1/3/6/7 under idx-26d earlier the same day. Same
+page, same stamp date — but one is inherited, not re-run, and idx-26f's resolution now
+says so in those terms rather than presenting all six as a single verification.
+
 **Queue state: 6 open, 8 resolved.** Suite 1047/1047.
 
 ## Appendix A — the 15 admitted proposals, hand-verified

scripts/kb-eval/data/g7-review-queue.json

@@ -161,7 +161,7 @@
         "2. **Fairness insights**: Performance disparities across sensitive groups (gender, ethnicity, age)",
         "5. **Data analysis**: Dataset statistics, missing values, outlier analysis"
       ],
-      "resolution": "Operator-ratified 2026-08-03, form (a): descriptions rewritten to the source's own wording, NOT surgical deletion of the named parentheticals. The source was re-fetched live before writing (how-to-responsible-ai-scorecard) and states only \"how well your model is satisfying the fairness target values you set for your desired sensitive groups\" and \"The data analysis segment shows you characteristics of your data\". Item 2 is now \"Hvor godt modellen moeter fairness-target values du har satt for de sensitive gruppene du velger\" and item 5 \"Karakteristikker ved dataene dine\" (both written with correct Norwegian diacritics in the corpus file). Deleting only the specificity this entry NAMED was rejected on two counts, each of which would have made the repair inherit the defect class it was raised against: it leaves item 5 as \"Dataset statistics\", which the source does not state either and which this entry did NOT adjudicate as checked-and-clear the way it did item 4; and it leaves item 2 as \"across sensitive groups\", dropping the you-choose-them agency and stranding item 2 in the pre-idx-26d dialect while items 1, 3, 6 and 7 carry \"du har satt\" - reopening the mixed-dialect defect idx-26d was booked under, in the file idx-26d had just canonicalised. Form (b) - narrowing the stamp's stated reach in the file instead - was put to the operator and declined: it is honest-by-annotation relocated from this queue's resolution field into the corpus, i.e. the same mechanism this entry exists to remove the need for. Item 4 was left untouched per this entry's own adjudication. Cross-file grep before editing: \"gender, ethnicity, age\", \"outlier analysis\" and \"Dataset statistics\" occurred nowhere else in the corpus. The enumeration was re-read whole after the edit for coherence, not just for the two edited strings. SUPERSEDES the closing clause of idx-26d's resolution: what the **Confidence:** Verified (MCP: microsoft-learn, 2026-08-03) stamp vouches for is now a seven-member enumeration whose names are all the source's own segment names, whose descriptions for items 1, 2, 3, 5, 6 and 7 were verified against the live source on the date the stamp carries, and whose item 4 description was adjudicated a recognisable paraphrase of the source's causal-insights passage. No exception is written down anywhere for the stamp to remain honest."
+      "resolution": "Operator-ratified 2026-08-03, form (a): descriptions rewritten to the source's own wording, NOT surgical deletion of the named parentheticals. The source was re-fetched live before writing (how-to-responsible-ai-scorecard) and states only \"how well your model is satisfying the fairness target values you set for your desired sensitive groups\" and \"The data analysis segment shows you characteristics of your data\". Item 2 is now \"Hvor godt modellen moeter fairness-maalverdiene du har satt for de sensitive gruppene du velger\" and item 5 \"Karakteristikker ved dataene dine\" (both written with correct Norwegian diacritics in the corpus file). Deleting only the specificity this entry NAMED was rejected on two counts, each of which would have made the repair inherit the defect class it was raised against: it leaves item 5 as \"Dataset statistics\", which the source does not state either and which this entry did NOT adjudicate as checked-and-clear the way it did item 4; and it leaves item 2 as \"across sensitive groups\", dropping the you-choose-them agency and stranding item 2 in the pre-idx-26d dialect while items 1, 3, 6 and 7 carry \"du har satt\" - reopening the mixed-dialect defect idx-26d was booked under, in the file idx-26d had just canonicalised. Form (b) - narrowing the stamp's stated reach in the file instead - was put to the operator and declined: it is honest-by-annotation relocated from this queue's resolution field into the corpus, i.e. the same mechanism this entry exists to remove the need for. Item 4 was left untouched per this entry's own adjudication. Cross-file grep before editing: \"gender, ethnicity, age\", \"outlier analysis\" and \"Dataset statistics\" occurred nowhere else in the corpus. The enumeration was re-read whole after the edit for coherence, not just for the two edited strings. SUPERSEDES the closing clause of idx-26d's resolution: what the **Confidence:** Verified (MCP: microsoft-learn, 2026-08-03) stamp vouches for is now a seven-member enumeration whose names are all the source's own segment names, whose descriptions for items 2 and 5 were re-verified against the live source THIS session and whose descriptions for items 1, 3, 6 and 7 were verified against the live source under idx-26d earlier the same day - the same stamp date and the same page, but an inherited verification rather than one re-run here, stated separately so the artefact is honest about its own provenance, and whose item 4 description was adjudicated a recognisable paraphrase of the source's causal-insights passage. No exception is written down anywhere for the stamp to remain honest. POST-EDIT CORRECTION, same session: item 2 first landed as \"fairness-target values\", a hybrid compound that is neither language and that broke the very dialect consistency this repair was justified by - item 1 renders the same source concept as \"target-verdiene\". Corrected to \"fairness-maalverdiene\". The operator-ratified LABEL was \"kildens ordlyd i idx-26d-dialekten\"; the illustrative preview carried the defective form, and the label is the ratified object, so the correction needed no re-ratification. The coherence re-read after the first edit checked the enumeration for CONTENT alignment and passed it - it did not check compound forms, which is the axis that failed."
     },
     {
       "id": "idx-27c",

skills/ms-ai-governance/references/responsible-ai/transparency-documentation-standards.md

@@ -112,7 +112,7 @@ PDF-rapport designet for å dele model- og data-innsikter mellom tekniske og ikk
 **Komponenter i Scorecard:**
 
 1. **Summary / model overview**: Modelloversikt og de target-verdiene du har satt
-2. **Fairness insights**: Hvor godt modellen møter fairness-target values du har satt for de sensitive gruppene du velger
+2. **Fairness insights**: Hvor godt modellen møter fairness-målverdiene du har satt for de sensitive gruppene du velger
 3. **Top important factors**: Faktorene som påvirker modellens prediksjoner mest
 4. **Causal insights**: Causal vs correlational relationships i features
 5. **Data analysis**: Karakteristikker ved dataene dine