Scanners on Quadrant IntegrityLens

Unicode Characters

Mon, 01 Jan 0001 00:00:00 +0000

Unicode Character Scanners#

These scanners detect special Unicode characters that AI models (ChatGPT, Copilot, etc.) frequently insert into text but that students almost never type manually. They run regardless of the selected language.

Scanner ID	Character	Example	Confidence
`em-dash`	U+2014 — (em dash)	“Text — more text” instead of “Text - more text”	High
`en-dash-word-join`	U+2013 – between letters	“word–joiner” instead of “word-joiner”	High
`smart-quotes`	U+201D " and U+2018 '	“quoted” instead of “quoted”	Medium / Low
`ellipsis`	U+2026 … (horizontal ellipsis)	“and so on…” instead of “and so on…”	Medium
`non-breaking-space`	U+00A0 (non-breaking space)	Invisible — looks like a normal space	Medium
`invisible-space`	U+200B, U+200A, U+2009, U+202F, U+FEFF	Completely invisible zero-width characters	High
`minus-sign`	U+2212 − (minus sign)	“5 − 3” instead of “5 - 3”	Medium

Why these matter#

When students type text in a word processor, they use the standard keyboard characters: hyphens (-), straight quotes ("), three dots (...), and regular spaces. AI models, however, are trained on typographically polished text and tend to output Unicode variants of these characters.

German Language

Mon, 01 Jan 0001 00:00:00 +0000

German Language Scanners#

These scanners detect patterns specific to German text and only run when the language is set to deu (the default).

Umlaut digraphs (`german`)#

AI models sometimes replace German umlauts (ä, ö, ü) with ASCII digraphs (ae, oe, ue). This scanner detects such substitutions.

To avoid false positives, Quadrant IntegrityLens uses an allowlist of approximately 4,500 known German words that contain umlauts. A digraph is only flagged if the word (or a compound suffix) has a known umlaut form. This means English loanwords like “poem” or legitimate German words like “Abenteuer” (adventure) are not flagged.

Swiss German

Mon, 01 Jan 0001 00:00:00 +0000

Swiss German Scanner#

Eszett detection (`swiss-german`)#

Swiss Standard German never uses the Eszett (ß) — it always uses “ss” instead. For example:

Meaning	Standard German (Germany)	Swiss Standard German
street	Straße	Strasse
big	groß	gross
moreover	außerdem	ausserdem

AI language models are predominantly trained on German text from Germany and therefore produce ß regularly. When a student submission written in Swiss German contains Eszett characters, this is a strong indicator that the text was not written by the student.

Rhetorical Patterns

Mon, 01 Jan 0001 00:00:00 +0000

Rhetorical Pattern Scanners#

These scanners detect rhetorical writing patterns that AI models overuse in German text. They only run when the language is set to deu.

A single occurrence of these patterns is normal in student writing. The scanners only trigger when patterns appear two or more times, and confidence increases with frequency.

Negative parallelism (`negative-parallelism`)#

Detects parallel negation constructions such as “Not only X, but also Y” and “Neither X nor Y”. The scanner matches the German equivalents of these patterns.

Structural Patterns

Mon, 01 Jan 0001 00:00:00 +0000

Structural Pattern Scanners#

These scanners detect formatting patterns and textual artifacts that are characteristic of AI-generated content. They run regardless of the selected language.

Label lists (`label-list`)#

Detects AI-style lists where each item starts with a bold label followed by a description:

Clarity: The text should be easy to understand. Brevity: Keep sentences short. Accuracy: Facts must be verified.

Students writing lists typically use plain bullet points without bold labels.

Scanners on Quadrant IntegrityLens

Unicode Characters

Unicode Character Scanners#

Why these matter#

German Language

German Language Scanners#

Umlaut digraphs (german)#

Swiss German

Swiss German Scanner#

Eszett detection (swiss-german)#

Rhetorical Patterns

Rhetorical Pattern Scanners#

Negative parallelism (negative-parallelism)#

Structural Patterns

Structural Pattern Scanners#

Label lists (label-list)#

Umlaut digraphs (`german`)#

Eszett detection (`swiss-german`)#

Negative parallelism (`negative-parallelism`)#

Label lists (`label-list`)#