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>
This commit is contained in:
2026-08-05 12:08:14 +08:00
parent 2d90d05bc5
commit 61234fe36b
46 changed files with 154 additions and 128 deletions

View File

@@ -132,7 +132,7 @@ INSTRUCTION: Answer the question aloud.
INPUT: speak
CHECK: llm
SHOW_PROMPT
RUBRIC: Accept a short or full sentence identifying the correct job (e.g., "He's a pilot.").
RUBRIC: Accept a short or full sentence identifying the correct job (e.g., "He's a pilot."). Accept common synonyms for the same job (e.g. "mailman" for "mail carrier", "taxi driver" / "cab driver").
EXAMPLE
PROMPT: Tom has a small class of ten students. What's his job?
@@ -646,7 +646,7 @@ ACCEPT: pilot
PROMPT: Mathematics is also called something else. What's it called? {bk07-l1b-f2-05-q.mp3}
TEMPLATE: It's also called ____.
RESPONSE: It's also called math. {bk07-l1b-f2-05-a.mp3}
ACCEPT: math
ACCEPT: math | maths | It's also called maths.
PROMPT: This shape is like the letter O. What's it called? {bk07-l1b-f2-06-q.mp3}
TEMPLATE: It's called a ____.
@@ -1178,6 +1178,7 @@ PROMPT: {st-page_029_003.jpg}
RESPONSE: Both test grades are 40. Both grades are bad.
PROMPT: {st-page_029_004.jpg}
RUBRIC: This picture shows a single circle drawn with a mistake — it is not closed. Accept any sensible description of that fact; "one"/"the other"/"both" are not required for this item.
RESPONSE: It is a circle, but it has a mistake. It is not closed.
PROMPT: {st-page_029_005.jpg}
@@ -1505,7 +1506,7 @@ INTRO: Now describe pictures with the new adjectives. Look at each one and say w
INSTRUCTION: Look at the picture and describe what you see.
INPUT: speak
CHECK: llm
RUBRIC: Treat the model answer as the key; accept any sentence using the same adjective for the same object (e.g., "a little circle", "a strong man").
RUBRIC: Treat the model answer as the key; accept any sentence or standalone noun phrase using the same adjective for the same object (e.g. "a wide street", "It is a wide street.").
PROMPT: {st-page_032_001.jpg}
RESPONSE: I see a little circle.