buvard
v0.1.2
Published
buvard — l'anti-slop qui tache. Blotting paper for AI-flavored prose: a weighted multi-score linter for French and English slop patterns.
Maintainers
Readme
buvard
L'anti-slop qui tache. Blotting paper for AI-flavored prose: a weighted, multi-score linter for French and English slop patterns. It absorbs what baves — the empty openers, the inflated adjectives, the "Ce n'est pas X, c'est Y" pivots, the tirets cadratins by the dozen.
One catalog, clustered from five anti-slop sources (two French skills, two bilingual frameworks, one EN framework), scored by a ratified barème, and tested. Zero config, by design — like black, the formatting is the tool's; the words stay the author's.
git clone https://git.nech.pl/pln/buvard.git && cd buvard
sudo ln -sf "$PWD/bin/buvard.js" /usr/local/bin/buvard
buvard check posts/ # scores + grouped hits, per file
buvard check article.md --json # machine-readable, for pipelinesThe barème
Score starts at 100. A lexique hit costs 5, a structure hit 8, servility or
meta-commentary 10. Punctuation runs on budgets: one tiret cadratin per 500
words, one ! per 1000 — each excess occurrence costs 5.
- 100–90 — publish.
- 80–95 — real hits only; fix what reads wrong.
- <80 — rewrite pass, then re-run. The score is a smoke alarm, not a grade.
Every hit is a review candidate, not a verdict. Never touch: the author's ideas, data, deliberate jargon, quoted speech, or the voice.
Scope and honesty
buvard is a style linter, not an AI detector. It finds statistically over-represented patterns; it cannot and does not claim to detect machine authorship. Its catalog is deliberately regex-shaped (high precision, low recall): règle de trois, synonyme acrobatique and sentence-length monotony stay manual checks. See Science and references for the evidence behind the catalog.
Agents
Agents run buvard three ways, in order of friction:
npx buvard check . # after npm publish — no install at all
node bin/buvard.js check . # from a clone — zero dependencies, Node >= 18
buvard check . # global symlink (see install above)AGENTS.md carries the project handoff for any agent; SKILL.md packages the
catalog as an agent skill: load it, run the linter, apply the findings by hand.
Hits are review candidates, never verdicts — the agent edits prose like an
editor, not like a filter.
Science and references
The catalog is data with provenance, and the barème is a ratified decision — both are written down:
- docs/research.md — the clustering study: five anti-slop sources (fr1, fr2, étape, no-slop, ui-sk), what each contributes, and how the shared patterns became the catalog.
- docs/research-litreview.md — the literature review on AI-text detection, and the ten falsifiable recommendations that will become catalog v3. Read it before touching the catalog.
Core citations, one line each — the lit review holds the full bibliography:
- Liang et al., 2023 — GPT detectors are biased against non-native English writers: a 61.22% false-positive rate on TOEFL essays. The case for staying a linter.
- MULTITuDE — the large multilingual detection benchmark omits French; INRIA's French ChatGPT-detection study shows French is open territory.
- GLTR, DetectGPT, Binoculars — the detection toolbox; each degrades on short or paraphrased text.
- Sadasivan et al., 2024 — paraphrase attacks collapse detection on ~300-token passages. Why buvard never plays that game.
- Kobak et al., 2024 — excess vocabulary as a population-level AI marker. A cousin of our lexique.
- Sibling linters — proselint and Vale are the ancestors; Wikipedia's "Signs of AI writing" is the shared folklore.
Methodology, going forward (catalog v3): every new rule must pass a false-positive gate — under 2% per rule on a pre-2022 Gutenberg corpus, human-written by construction. Model-generated text is used only to measure sensitivity, never to admit a rule; a catalog tuned on one model's slop learns that model's fingerprints.
Skill
SKILL.md ships the catalog as an agent skill: load it, run the linter,
apply the findings by hand. The remedies are content, not code.
License
GPL-3.0-only — see LICENSE. The name: a buvard is blotting paper; it exists because l'encre bave.
