Make embedded references canonical

QBANK_PDF_IMPORT_RUNBOOK.md

@@ -25,10 +25,10 @@ distinctive fact combinations, answer wording, or images.
   mismatches.
 
 Known gap in that historical run: model-based medical review was completed, but
-authoritative references were not added to `QUESTION_REFERENCE_REVIEWS.md` for
-the `nbme5-*` records. Future runs must complete the reference-review gate below
-before setting `isPublished` to `true`. The historical records should be treated
-as awaiting that separate reference review.
+authoritative references were not embedded in the `nbme5-*` question documents.
+Future runs must complete the reference-review gate below before setting
+`isPublished` to `true`. The historical records should be treated as awaiting
+that separate reference review.
 
 ## Prerequisites
 
@@ -169,6 +169,8 @@ The generation prompt must require:
 - Celsius and Fahrenheit together for every temperature;
 - labs only when useful and only when their values also appear in the stem;
 - `media: []` unless separately reviewed, licensed media will be added later;
+- a `references` array that the reference-review gate populates with complete
+  authoritative source records before publication;
 - selection percentages for every authored choice initialized to zero;
 - established Step categories, 3-6 tags, and a unique deterministic ID.
 
@@ -236,8 +238,9 @@ Model agreement is not authoritative medical verification. Before publication:
 1. Verify each keyed answer and material explanatory claim against current,
    direct, authoritative sources such as professional guidelines, government
    agencies, official labeling, or primary research.
-2. Add an entry for every question to `QUESTION_REFERENCE_REVIEWS.md`, including
-   title, publisher, direct URL, supported claim, access date, and reviewer.
+2. Add every verified source to the question document's `references` array,
+   including title, publisher, direct HTTPS URL, supported claim, ISO access
+   date, and reviewer. Do not maintain a separate repository reference ledger.
 3. Search the entire question bank for exact and near-duplicate learning tasks,
    not just duplicate text or IDs.
 4. Record duplicate-review dispositions and substantially differentiate or
@@ -280,6 +283,7 @@ Verification is complete only when all of these pass:
 - the API reports the expected upsert count;
 - the database contains every expected external ID exactly once;
 - every stored `correctChoiceId` matches the final payload;
+- every stored `references` array exactly matches the verified payload;
 - a targeted deployed-API search returns at least one newly inserted question;
 - the returned question has the expected choices, answer key, and publication
   state;
@@ -304,9 +308,10 @@ API_READ_RESULTS=<count>
 
 ## 10. Retain Reviews, Then Clean Up
 
-Retain the reference ledger, duplicate-review record, validation summary, audit
-decisions, and final ID/answer-key manifest according to project policy. These
-are review records, not disposable generation scratch files.
+Retain authoritative references in each question document. Retain the
+duplicate-review record, validation summary, audit decisions, and final
+ID/answer-key manifest according to project policy. These are review records,
+not disposable generation scratch files.
 
 After production verification:
 
@@ -332,7 +337,7 @@ generated-artifact cleanup.
 - [ ] All anchoring and source-overlap warnings reviewed.
 - [ ] Independent content audit approved every question.
 - [ ] Every rejected question regenerated and re-audited.
-- [ ] Authoritative references recorded for every question.
+- [ ] Authoritative references embedded in every question document.
 - [ ] Full-bank duplicate review completed.
 - [ ] Image rights cleared for every media-bearing question.
 - [ ] Final payload contains only intended new or intentionally updated IDs.