Skip to content

Latest commit

 

History

History
130 lines (89 loc) · 5.07 KB

File metadata and controls

130 lines (89 loc) · 5.07 KB

Glossary

Short definitions for recurring patina terms. Each entry links to the deeper reference where the term is used in context.

AI-likeness

A 0-100 editing signal for how strongly a text matches patina's AI-writing patterns. Lower means less AI-sounding; it is not proof of authorship. See the scoring overview and the FAQ.

Audit mode

The mode that detects and reports AI-writing patterns without rewriting the text. Use it when you want to inspect what patina would flag before changing anything. See the mode table and examples guide.

Burstiness

The variation in sentence length inside a paragraph, measured with coefficient of variation. Very uniform sentence lengths are one signal that a paragraph may need closer inspection. See Stylometry.

Diff mode

The mode that shows changes pattern by pattern, making the edit auditable instead of a black-box paraphrase. See the mode table and examples checklist.

Document Type

The document-policy axis. It selects purpose, audience, structural conventions, domain vocabulary/precision, avoidance rules, and language-scoped pattern bounds without changing Persona voice, Register, or meaning thresholds. CLI: --document-type; config: document-type. The historical ids formal and casual-conversation refer to structured-document and chat/message conventions; they do not select professional or casual Register.

Fidelity

A meaning-accuracy score comparing original text with a rewrite. Higher is better: it checks whether claims, facts, audience/register, and length stayed faithful. See Fidelity Scoring.

Meaning preservation

The safety goal that rewritten text should keep the original claims, polarity, causal links, numbers, and other high-risk details. See the FAQ and MPS overview.

MATTR

Moving Average Type-Token Ratio, a lexical-diversity metric that reduces the length bias of simple TTR. Patina uses it as one stylometry signal, with known language limitations. See Stylometry.

Mode

A CLI output path such as rewrite, audit, score, or diff. Modes control whether patina edits text or reports findings. --verify is a rewrite modifier, not a separate mode. See the mode table.

MPS

Meaning Preservation Score. MPS checks whether extracted semantic anchors survive the rewrite pipeline and whether polarity is preserved. See the FAQ and MPS scoring.

Pattern

A named AI-writing signal with a fire condition, exclusion condition, problem description, and before/after example. Patterns are the unit patina audits and rewrites against. See PATTERNS.md.

Pattern pack

A language and category file such as patterns/en-style.md or patterns/ko-content.md. Packs group related patterns and provide counts used by scoring. See PATTERNS.md.

Persona

An optional, reusable voice fingerprint. Persona v2 may shape vocabulary, rhythm, metaphors, and explanation habits; it cannot select Document Type, Register, pattern policy, or meaning thresholds. Omitting --persona preserves the source voice.

Register

The casual or professional delivery axis: wording and sentence-ending markers only. Omitting --register preserves the source register. Genre values such as academic and marketing are Document Types, while idiolect and rhythm belong to Persona.

Rewrite mode

The default mode that removes matched AI-writing patterns while checking that meaning survived the edit. See the Quick Start and MPS integration points.

Score mode

The mode that returns a 0-100 AI-likeness score. Default scoring combines LLM-judged categories with deterministic signals; --offline reports the deterministic subset without a backend. See Score Interpretation.

Semantic anchor

A meaning unit extracted before rewriting, such as a claim, negation, number, causal link, quantifier, or polarity marker. Anchors are later verified by MPS. See MPS Anchor Verification Criteria.

Suspect zone

A paragraph or sentence group marked for closer inspection by stylometry, usually because burstiness, MATTR, or lexicon signals fired. See the stylometry delivery format.

Viral hook

A score-only pattern class for SNS and marketing signals such as shock numbers, clickbait closes, source-skipping authority claims, short-sentence stacking, and hyperbolic engagement language. See Score-only viral hooks.