ocertat/cmos
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

exemplars: canary for CMOS 8.159 preposition rule (Huttunen, Mehra)

Browse Source 
Two new real-draft-derived journal exemplars locking down prompt
rule 29 from the preceding commit. Follows the Hasanah precedent
for promoting real-draft failures into the canary corpus, per the
"defense in depth" feedback in project memory.

- journal_preposition_huttunen.toml exercises "among" mid-title,
  plus four other CMOS 8.159 lowercased words ("on", "in", "a",
  and implicitly "among"). Real article: Huttunen and Kortelainen,
  JASIST 72, no. 7 (2021). The messy_input uses the ASCII hyphen
  in "Meaning-Making" for clarity — the source draft actually had
  a U+2010 non-breaking hyphen from docx->txt conversion, but
  mixing Unicode hyphen normalization into this exemplar would
  have conflated two independent failure modes. The U+2010 issue
  is noted in the exemplar comment for a separate iteration.

- journal_preposition_mehra.toml exercises "beyond" mid-title,
  plus mid-title exclamation-point preservation (rule 25) and
  leading-"The" drop from "The Library Quarterly" (rule 17).
  Real article: Mehra, Library Quarterly 91, no. 2 (2021).

Both are canary-enabled and will block any future prompt iteration
that regresses on these patterns via the exact-match canary axis.
The canonical dicts additionally lock them down via the field-
level diff, per the upstream-refinement feedback in project
memory.

Canary corpus size: 15 -> 17.
This commit is contained in:
Mark Eaton
2026-04-11 15:30:02 -04:00
parent 0238f5e5d7
commit 1d970e84f9
2 changed files with 77 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
exemplars/journal_preposition_mehra.toml
+36
View File
@@ -0,0 +1,36 @@
# Source: derived from a real-world entry in the user's HML draft (Mehra,
# Library Quarterly 91, no. 2, 2021). Promoted to exemplar during real-draft
# testing on 2026-04-11 after the formatter was observed capitalizing
# "Beyond" mid-title, violating CMOS 8.159 ("lowercase prepositions
# regardless of length in headline-style capitalization").
#
# This exemplar complements journal_preposition_huttunen.toml with a
# different preposition ("beyond" instead of "among"), which verifies that
# new prompt rule 29 generalizes across the preposition list rather than
# getting memorized for a single word.
#
# Also exercises:
# - Mid-title exclamation point in the article title ("Enough Crocodile
# Tears!") must be preserved verbatim, not replaced with a period
# (rule 25)
# - Leading "The" dropped from the periodical name: "The Library Quarterly"
# → "Library Quarterly" (rule 17)
# - Inclusive-number elision within the 110–199 band: 137-149 → 137–49
# (rule 24)
# - Curly quote → straight quote normalization
source = "user draft (HML Submission); article: Mehra, Library Quarterly 91, no. 2 (2021), https://doi.org/10.1086/713046"
type = "journal"
tags = ["journal", "single-author", "cmos-8.159", "headline-case", "preposition", "leading-the-drop", "terminal-punctuation"]
canary = true
messy_input = "Mehra, Bharat. “Enough Crocodile Tears! Libraries Moving beyond Performative Antiracist Politics.” The Library Quarterly 91, no. 2 (2021): 137-149. https://doi.org/10.1086/713046."
expected_bibliography = "Mehra, Bharat. \"Enough Crocodile Tears! Libraries Moving beyond Performative Antiracist Politics.\" *Library Quarterly* 91, no. 2 (2021): 137–49. https://doi.org/10.1086/713046."
[canonical]
author = "Mehra, Bharat"
article_title = "Enough Crocodile Tears! Libraries Moving beyond Performative Antiracist Politics"
journal = "Library Quarterly"
volume = 91
issue = 2
year = 2021
pages = "137–49"
doi = "https://doi.org/10.1086/713046"