apply answerability-audit repair queue: ACCEPT variants, derivability fixes, rubric rewrites (46 masters)

- MISSING_ALTERNATIVES (63/64 applied): uncontracted/contracted forms, digit
  variants (05|5), synonyms and full-sentence variants, via ACCEPT lines and
  inline gap alternatives; skipped 'better/fine' for the Opposites drill (not
  opposites of "sick").
- NOT_DERIVABLE (16 fixed, 10 false alarms, 1 skipped): item-level fixes
  (visible word hints, missing premise, speaker clarifications "Joe (to Jim):",
  emphasis/cue corrections, un-gapped unguessable words, rounded-number
  accepts); converted the two book-10 paragraph clozes (Mary / The Mall) from
  CHECK: exact to CHECK: llm with logical-completion rubrics; cross-book
  recycled vocab (pilot, teller, barber, variety store, ...) left alone.
- UNCLEAR_TARGET (10): instruction/intro corrections (Food "Type the word for
  the food.", Explain-with-Too intro), cue/emphasis fixes.
- Rubric rewrites (57): applied audit-suggested grader rubrics (now effective
  with the pre-item RUBRIC parser fix); moved the two per-item rubrics of
  book-11 "Write the Main Idea" inside their items.

No clip-bearing line changed; all masters validate (0 errors, 0 new warnings)
and pass stage-master clip-identity checks. Full decision log:
reactor-module-tools module-convert/answerability-audit/APPLIED.md

Co-authored-by: Cursor <cursoragent@cursor.com>

book-4-lesson-3.module

@@ -1005,7 +1005,7 @@ INTRO: This time you get the answer first and must supply the question — "who"
 INSTRUCTION: Say a "who" or "what" question with "can" that fits the answer.
 INPUT: speak
 CHECK: llm
-RUBRIC: The learner must form a question starting with "Who can..." or "What languages can..." that correctly elicits the provided model answer. The question form is the point; minor wording differences are fine.
+RUBRIC: The learner must form a question starting with "Who can..." or "What languages can..." that elicits the statement. Accept pronouns used in the prompt (e.g. "he") even if the model answer uses a specific name, and omitting context not shown in the prompt. The correct question form with "can" is the point.
 
 EXAMPLE
 TEMPLATE: ____
@@ -1492,7 +1492,7 @@ INSTRUCTION: Answer the question using "must" and the cue.
 INPUT: speak
 CHECK: llm
 SHOW_PROMPT
-RUBRIC: Accept a correctly formed sentence using "must" that answers the question using the cue (e.g. "I must wear my uniform."). "Must" plus the cued verb is the point; extra words are fine.
+RUBRIC: Accept any correctly formed sentence using "must" and the cued word or a reasonable synonym (e.g. "wear" for "put on"). "Must" plus the cued word is the point; extra words or minor determiner changes are fine.
 
 EXAMPLE
 PROMPT: You have a test tomorrow. What must you do?