main
5
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Mark Eaton
|
c21ca7b58e |
v2 chunk 5: 5 fixes from cross-draft triage (HML + Reading_Disrepair)
After chunk 4 verification on the Anti-Communist draft, ran v2
against the previously-untested ## Notes sections of HML (72 notes)
and Reading_Disrepair (25 notes) — 97 new notes for 204 total
across 3 drafts. The wider corpus surfaced 5 distinct issues that
weren't visible in the Anti-Communist data alone.
src/cmos/note_formatter.py:
1. Tighten substantive prose detector — exclude semicolon-bearing
inputs (chunk 5 task 1). The HML draft was dominated by compound
shortened references like:
See Author1, "Title;" Author2, "Title;" Author3, "Title."
17 of 72 HML notes matched this pattern, exceeded the 150-char
threshold, and had no citation skeleton markers, so they were
passed through verbatim by the chunk 3 detector. Compound
references use semicolons as item separators; substantive prose
doesn't. Adding `if ";" in stripped: return False` cleanly
separates the two without affecting the genuine substantive
notes (which contain none).
2. Rule 3 — distinguish comma-inside vs period-inside for
article/chapter title closing quote based on whether MORE
content follows the title. Surfaced by 8+ entries across drafts
producing the wrong `"Title,".` pattern (comma inside followed
by stray period outside) when the title is the last element of
the entry. Rule 3 now explicitly says: comma inside when more
content follows; period inside when title is the last element.
3. New rule 20 — preserve signal phrases verbatim. Surfaced by HML
[69] and [70] where "For example," was stripped while "See" was
preserved elsewhere. CMOS notes commonly open with signal
phrases (See, See also, For example, Cf., Compare, But see,
Contra, Accord, Quoted in) that indicate how a citation relates
to the surrounding argument. Stripping them is data loss.
4. Rule 1 — explicit "no comma between author name and 'et al.'"
in non-inverted note form. Surfaced by HML [69] where "Bignoli
et al." became "Bignoli, et al." (extra comma). The comma
before "et al." is a feature of inverted bibliography form,
not non-inverted note form. Rule 1 now includes WRONG examples.
5. Citation skeleton URL marker — also accept bare-domain URLs
without the https:// scheme. Surfaced by Reading_Disrepair [1]
GAO entry which had `files.gao.gov/...` without `https://`,
so the existing https?:// marker didn't match and the 190-char
citation was passed through as substantive prose. New pattern:
`\b\w{2,}(?:\.\w{2,})+/\S*` catches bare domains like
files.gao.gov/path without false-positiving on common things
like "e.g./" (single-char tokens excluded by {2,}).
Tests: 157/157 (was 153, +4 net new for prompt-content and regex
verification). The +4 is: compound-reference detection, genuine
substantive prose regression check, rule 3 / rule 20 / rule 1
prompt-content tests, bare-domain URL detection.
Path B: rule 18 (publishers, chunk 4) and rule 20 (signal phrases,
this commit) are v2-only. Rule 1 et al. clarification could in
principle apply to v1 too but v1 doesn't see "et al." in the same
non-inverted form. v1 untouched. 96/96 v1 tests still passing.
Real-draft validation pending — verification re-run against all
3 drafts will follow in the next step.
|
||
|
Mark Eaton
|
83339e313c |
v2 chunk 4: revert validator carve-out + expand publisher exceptions
Two follow-ups based on the chunk 3 verification re-run findings. src/cmos/runtime_validator.py — revert chunk 3 fix #3 (carve-out) Chunk 3 fix #3 added a carve-out so shortened-form notes ("Rosen, 7.", "Ettarh.") would pass the validator without italics, saving retry cost. Chunk 3 verification on the Anti-Communist draft showed the carve-out also let GPT-5's variance produce under-italicized variants of shortened forms WITH short titles (e.g., "A Restudy, 73." instead of the more CMOS-correct "*A Restudy*, 73."). The user explicitly chose accuracy over the cost saving and asked for the carve-out to be reverted. The strict italics check now applies uniformly. Simple shortened forms (Mitchell, 197., Ettarh.) get retried unnecessarily and waste API cost without producing better output. Shortened forms with short titles get a fair shot at the italicized version on the retry. Cost ↑, accuracy ↑. Removes _SHORTENED_FORM_RE, _looks_like_shortened_form, and the carve-out check from validate(). Updates module docstring with history note. Inverts the 2 carve-out tests in test_runtime_validator.py to assert shortened forms now FAIL the strict check, documenting the design intent for future reviewers. src/cmos/note_formatter.py — expand rule 18 publisher exception list Chunk 3 verification showed [6] Batterson getting "NYU Press" expanded to "New York University Press", losing the publisher's canonical brand. Rule 18's exception list previously only named MIT Press, ALA Editions, and MLA. Expanded to include NYU Press, Routledge, IEEE Press, ACM Press, WHO Press, plus "Pew Research Center" as a non-Press canonical example. Also added a "when in doubt" guidance paragraph: if the abbreviation contains "Press" and is widely used as the publisher's own branding, leave it alone. The risk of losing a brand name (NYU Press) is worse than the risk of leaving an obscure abbreviation. v2 only. Tests: 151/151 green (was 150). The +1 is the new NYU Press prompt-content test; the 2 inverted runtime_validator tests stayed at the same count. Path B: runtime_validator change crosses the v1/v2 boundary (shared infrastructure), per the same approval that authorized the original chunk 3 fix #3. v1's bibliography formatter is unaffected in practice because v1 outputs always have italics. |
||
|
Mark Eaton
|
553240c153 |
v2 chunk 3: bug fixes from real-draft triage + polish
Six independent fixes addressing the Anti-Communist Formations of LIS real-draft test findings (chunk 2c). Four are bug fixes for issues that destroyed user data or wasted API calls; two are polish quality improvements revisited from the deferred list. src/cmos/note_formatter.py — empty input guard (fix #1) Empty / whitespace-only input now short-circuits the API entirely and returns the input verbatim. Surfaced by note [66] in the Anti-Communist draft, where GPT-5 broke character on empty input and returned a conversational meta-reply ("Please paste the citation entry...") that then got substituted into the document. Whitespace preserved so cli.reformat_notes is byte-exact on empty notes. v2 only. src/cmos/note_formatter.py — deprecated Latin guard (fix #2) New Python guard catches the full CMOS-18-deprecated Latin citation set (ibid, idem, id., op. cit., loc. cit.) and returns input verbatim before the API call. Rule 10 in the prompt also rewritten: explicitly says "return verbatim" instead of the old "return cleanest possible full-form note", which the model interpreted as "return empty when there's no information", silently destroying the marker. Surfaced by note [61] = "Ibid.". v2 only. src/cmos/runtime_validator.py — shortened-form carve-out (fix #3) The "must contain italics" check is now skipped when the candidate looks like a CMOS shortened-form note (author last name, optional page, no italic content). Surfaced by ~30 of 107 notes in the Anti-Communist draft that were correctly returned as shortened forms ("Rosen, 7.", "Mitchell, 197.") but rejected by the validator's strict italic check, firing the full retry budget on valid output (~60 wasted API calls per run). The carve-out is conservative: name-token regex + terminal period; doesn't match unstructured prose. Shared infrastructure — affects v1 and v2, no-op in v1's normal workflow because v1 outputs always have italics. src/cmos/note_formatter.py — substantive prose pass-through (fix #4) Long discursive prose with no citation skeleton markers now short-circuits the API and returns the input verbatim. Surfaced by notes [8] (689 chars), [9] (893 chars), [75] (163 chars) in the Anti-Communist draft — substantive notes that the formatter was extracting a single citation from and silently discarding the surrounding commentary. CMOS 14.39 explicitly allows substantive notes; preserving them is the user's explicit policy ("preserve all free text as long as that does not break other formatting"). Detection: length > 150 chars AND no citation skeleton markers (parenthesized year, URL, vol./no./pp., DOI, terminal page or terminal year). Conservative — does not false-positive on legitimate first-occurrence notes. v2 only. src/cmos/formatter.py + note_formatter.py — month/season preservation (polish #5) Both v1 rule 10 (journal article format) and v2 rule 5 (journal article note form) now explicitly instruct the model to preserve (Month YEAR) and (Season YEAR) parentheticals when the source provides them. Surfaced by entries in both Reading_Disrepair and Anti-Communist where (Spring, 1993) and August 1952 were silently collapsed to (1993) and 1952. Both forms are valid CMOS but month/season is more informative when the source has it. Affects v1 and v2 in mirror. src/cmos/note_formatter.py — government documents rule 19 (polish #7) v2 now has an explicit rule mirroring v1's rule 27: government bodies, institutional reports, and similar standalone documents get italicized titles and book-form treatment, NOT quoted-article treatment. Includes the Anti-Communist Senate of California Tenth Report and a hypothetical GAO example. Implicit handling worked in chunk 2c, but explicit rule provides regression protection. v2 only. Tests: +14 net new (across test_note_formatter.py, test_formatter.py, test_runtime_validator.py). Total suite 150/150 (was 136 before this chunk). All v1 tests still passing. Path B status: formatter.py and runtime_validator.py edits cross the v1/v2 boundary, but only by user-explicit approval per the relevant fix discussions. The shared validator was always shared; the v1 formatter rule 10 mirror is a small additive edit that doesn't affect the v1 prompt's existing behavior on its existing inputs. |
||
|
Mark Eaton
|
d061f78b7f |
v2 chunk 2a iter 1: rules 6+18 — ed. invariant, expand publishers
Two prompt edits to SYSTEM_PROMPT_NOTES driven by chunk 1 smoke test
gaps on chapter_first_doyle.toml.
Rule 6 (chapter form) expanded with an explicit invariance statement:
"ed." is the canonical abbreviation regardless of editor count — do
NOT pluralize to "eds." for multiple editors. CMOS NB treats it as
an invariant abbreviation, not a number-agreeing word.
New rule 18 (publisher expansion) mirrors v1 formatter.py rule 14:
publisher names must be in full canonical form, with note-form-
specific examples ("U of Chicago Press" → "University of Chicago
Press"). Includes the same MIT Press / ALA Editions / MLA carve-out
for publishers whose canonical self-presentation legitimately uses
initials.
Two new prompt-content unit tests added to tests/test_note_formatter.py
following the v1 test_formatter.py discipline. TDD cycle: red-green-
verified end-to-end.
Real-API smoke test, 3 v2 exemplars × 2 runs each: 6/6 byte-perfect
matches (was 4/6 in chunk 1; chapter_first_doyle went 0/2 → 2/2,
book and journal still 2/2). v1 untouched, 96/96 v1 tests still
passing. Total suite: 116/116.
|
||
|
Mark Eaton
|
28ca3ac928 |
v2 chunk 1: scaffold note formatter (Path B parallel artifact)
Begin v2 (in-text citation note form) as a parallel artifact to the
v1 bibliography formatter, per the Path B architectural decision:
no shared mutable state, no shared prompt content, no v1 changes.
New artifacts:
- src/cmos/parser.py: add find_notes() / NoteDefinition /
NotesParseResult as siblings to split_bibliography(). Targets
pandoc-style markdown footnote definitions [^marker]: text.
Single-line only; multi-line continuation deferred.
- src/cmos/note_formatter.py: new module mirroring formatter.py.
17-rule SYSTEM_PROMPT_NOTES for CMOS 18 first-occurrence note
form. Reuses cmos.runtime_validator.validate() unchanged — its
structural checks all apply to note form too. Caller injection,
retry loop, and model selection mirror v1.
- tests/test_parser.py: 7 new tests for find_notes().
- tests/test_note_formatter.py: 11 new tests mirroring v1 test
discipline (no API calls, fake-caller injection, retry semantics,
prompt smoke checks).
- exemplars/notes/: new subdirectory with 3 hand-synthesized
first-occurrence note exemplars (book, journal article, chapter
in edited book). Uses expected_note as the field name (not v1's
expected_bibliography). harness/score.py:load_exemplars uses a
non-recursive glob, so the v1 canary loader does not see these —
Path B isolation is automatic.
v1 untouched. v1 canary still loads exactly 17 exemplars. Full
test suite: 96 v1 + 18 new v2 = 114 passing.
Smoke-tested all 3 v2 exemplars against real GPT-5 (not fakes),
2 runs each. book_first_yu and journal_first_kwon: 4/4 byte-perfect
on the first try. chapter_first_doyle: 0/2, surfacing two known
prompt gaps for the next iteration:
1. Publisher abbreviation not expanded ("U of Chicago Press"
preserved instead of "University of Chicago Press"). v1's
formatter.py rule 14 is missing from the v2 prompt.
2. "ed." pluralized to "eds." for multiple editors. CMOS NB
uses "ed." invariantly regardless of editor count.
Both gaps are addressable prompt edits, not architectural problems —
exactly the kind of finding the dev loop is designed to surface.
Out of scope (deferred to chunk 2 and later): CLI extension,
shortened-form generation, document reassembly, harness scoring
loop integration, v2 linter rules, real-draft testing.
|