exemplars: canary for CMOS 8.159 preposition rule (Huttunen, Mehra)
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:
@@ -0,0 +1,41 @@
|
|||||||
|
# Source: derived from a real-world entry in the user's HML draft (Huttunen
|
||||||
|
# and Kortelainen, JASIST 72, no. 7, 2021). Promoted to exemplar during
|
||||||
|
# real-draft testing on 2026-04-11 after the formatter was observed
|
||||||
|
# capitalizing "Among" mid-title, violating CMOS 8.159 ("lowercase
|
||||||
|
# prepositions regardless of length in headline-style capitalization").
|
||||||
|
#
|
||||||
|
# The article title contains four words that CMOS 8.159 requires lowercase
|
||||||
|
# in headline-style caps: "on" (prep), "in" (prep), "a" (article), and
|
||||||
|
# "among" (prep). The formatter was observed inconsistently capitalizing
|
||||||
|
# "among" specifically — some HML entries correct, some not — which is
|
||||||
|
# the smoking-gun evidence of nondeterministic judgment drift the runtime
|
||||||
|
# validator cannot catch (it checks structural properties, not CMOS
|
||||||
|
# capitalization rules).
|
||||||
|
#
|
||||||
|
# Also exercises:
|
||||||
|
# - Curly quote → straight quote normalization
|
||||||
|
# - ASCII hyphen in page range → en-dash, no elision (crosses 800 boundary)
|
||||||
|
# - Two-author form: first inverted, second in First-Last order (rule 1)
|
||||||
|
#
|
||||||
|
# Note on simplification: the HML source entry contained U+2010 (non-
|
||||||
|
# breaking hyphen) in "Meaning‐Making", a docx→txt conversion artifact.
|
||||||
|
# This exemplar uses ASCII hyphen (U+002D) to avoid conflating two
|
||||||
|
# independent failure modes (preposition capitalization vs. Unicode
|
||||||
|
# hyphen normalization). The U+2010 issue is a separate finding and
|
||||||
|
# should be addressed in its own iteration if pursued.
|
||||||
|
source = "user draft (HML Submission); article: Huttunen and Kortelainen, JASIST 72, no. 7 (2021), https://doi.org/10.1002/asi.24447"
|
||||||
|
type = "journal"
|
||||||
|
tags = ["journal", "two-author", "cmos-8.159", "headline-case", "preposition"]
|
||||||
|
canary = true
|
||||||
|
messy_input = "Huttunen, Aira, and Terttu Kortelainen. “Meaning-Making on Gender: Deeply Meaningful Information in a Significant Life Change among Transgender People.” Journal of the Association for Information Science and Technology 72, no. 7 (2021): 799-810. https://doi.org/10.1002/asi.24447."
|
||||||
|
expected_bibliography = "Huttunen, Aira, and Terttu Kortelainen. \"Meaning-Making on Gender: Deeply Meaningful Information in a Significant Life Change among Transgender People.\" *Journal of the Association for Information Science and Technology* 72, no. 7 (2021): 799–810. https://doi.org/10.1002/asi.24447."
|
||||||
|
|
||||||
|
[canonical]
|
||||||
|
authors = "Huttunen, Aira, and Terttu Kortelainen"
|
||||||
|
article_title = "Meaning-Making on Gender: Deeply Meaningful Information in a Significant Life Change among Transgender People"
|
||||||
|
journal = "Journal of the Association for Information Science and Technology"
|
||||||
|
volume = 72
|
||||||
|
issue = 7
|
||||||
|
year = 2021
|
||||||
|
pages = "799–810"
|
||||||
|
doi = "https://doi.org/10.1002/asi.24447"
|
||||||
@@ -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"
|
||||||
Reference in New Issue
Block a user