WROITER’s Method

How the diagnostic works, where it breaks, and why we tell you both.

The diagnostic doesn’t render a verdict. The method pages below explain how the profile is built, what each pattern means, where the signals fail, and how we calibrate against real writing.

01
How It Works
How the profile is built, the six signal families, how to read what the diagnostic returns, and where the boundary between pattern overlap and authorship proof actually sits. Start here.
Detection logic · Core reference
02
Pattern Library
Every flag the diagnostic can raise, with a name, a description, a severity, and examples showing what the pattern looks like in real text.
50+ patterns · Rewrite guidance
03
Calibration Log
The books, datasets, thresholds, and before/after metrics behind every tuning decision. Updated each time the method changes.
Datasets · Threshold history
04
Limitations
False positives, false negatives, genre traps, and a safe review policy. Read this before using the diagnostic in any consequential decision.
Edge cases · Review policy
05
Changelog
A public record of every method change, interpretation update, and pattern addition. Timestamped and permanent.
Version history · Public record
06
Open Specification
Pattern Profile Specification v2.1: all 31 detectors across 6 signal families, output format, calibration harness, and known failure modes. Published for independent implementation and citation.
CC BY 4.0 · Citable reference
07
Engine Audit v1.3.4
We audited the engine. Three passes, 28 detectors, 57 findings. Three real code bugs (all small regex fixes). The spec was the laggard, not the engine. Full receipts published.
Three-pass review · Public findings JSON
Interpretation rule

A profile with many flags across many families means stronger overlap with AI-typical surface patterns. It is not proof of authorship, cheating, or intent, and it is never enough to skip human review. For the full interpretation framework, see How It Works. If policy is involved, read Limitations first.

Evidence before enforcement

Don’t turn the diagnostic into a decision without checking the evidence. Do AI Detectors Work? covers the reliability case. The False Positive Hall of Fame shows that false positives happen to real writing by real people. The research publishes the data behind every detection rule.