david/alc-english
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
- 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:
david
2026-08-05 12:08:14 +08:00
parent 2d90d05bc5
commit 61234fe36b
46 changed files with 154 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
book-7-lesson-3.module
View File

@@ -1694,7 +1694,7 @@ INPUT: speak
CHECK: llm
INTRO: Now you make both halves. Look at the picture, use the cue word to ask a superlative question — then answer it from what you see. The examples show the pattern.
INSTRUCTION: Ask a question with the cue word, then answer it.
RUBRIC: Accept a "who/which" superlative question using the cue word, followed by the correct matching answer; treat the model answer as the factual key for the answer half.
RUBRIC: Accept a superlative question using "who", "which", or "what" with the cue word, followed by the correct matching answer in full or short form; treat the model answer as the factual key for the answer half.
EXAMPLE
PROMPT: {st-page_112_001.jpg}
@@ -1975,7 +1975,7 @@ CHECK: llm
SHOW_PROMPT
INTRO: Now answer the question about that conversation aloud, in a full sentence.
INSTRUCTION: Answer aloud with a full sentence.
RUBRIC: The learner must state that Lieutenant Smith is sick.
RUBRIC: Accept any phrasing stating that Lt. Smith (or "he") is sick or ill, as a full sentence or short answer.
PROMPT: Why can't Lt Smith fly today? {bk07-l3c-f3-05-q.mp3}
RESPONSE: Because he's sick. {bk07-l3c-f3-05-a.mp3}
@@ -2001,7 +2001,7 @@ CHECK: llm
SHOW_PROMPT
INTRO: Now answer the question about the conversation at the gate, aloud and in a full sentence.
INSTRUCTION: Answer aloud with a full sentence.
RUBRIC: The learner must state that the sergeant checks ID cards after 6 o'clock at night.
RUBRIC: Accept any answer indicating that ID cards are checked after 6 o'clock at night (or "after 6 p.m."), in full-sentence or short form.
PROMPT: When does the sergeant have to check I.D. cards? {bk07-l3c-f3-11-q.mp3}
RESPONSE: Only after 6 o'clock at night. {bk07-l3c-f3-11-a.mp3}