Skip to content

Detector tell · 4 patterns · weight 3

The essay scaffolding everyone was taught to write

Four rows at weight 3 matching the signposts of a five-paragraph essay. They share a verdict floor with the formal connectors: hits of the two labels are counted together, and enough of them override the rest of the ensemble.

Our detector calls this category “Structural marker”. The patterns below are read out of functions/api/tools/detect.js when this page is built, and the examples are produced by running the shipped scorer over the 48 licensed samples in our benchmark. If a claim here stops matching the engine, the build fails.

What our own benchmark saw

Did not appear anywhere in the benchmark — no human sample and no AI sample. That is a fact about the benchmark. This label fires on text matching its own pattern; the probe below is run on every build and fails it if it stops.

We are not going to invent an example to fill the gap. What we can show instead is a sentence we wrote ourselves, purely to check that the rule is live.

A constructed example — written by us, not evidence

This sentence was written for this check. It is not from the benchmark, nobody wrote it as real prose, and it says nothing about how anyone writes. Its only job is to prove the rule still fires, and the generator fails the build if it stops.

“In conclusion, the pilot should be extended by one term.”

  • /\bin conclusion\b/gi → “In conclusion”

What it means when a person writes this way

Anybody schooled on the five-paragraph essay writes "In conclusion". Anybody writing a summary section of a report writes "In summary". The engine's own source note claims human prose "almost never" uses these in running text — that claim is not measured anywhere in our benchmark, and this page is not the place to launder it into a fact. It is, however, the stated reason these rows carry weight 3 instead of 2. What is measured is in the benchmark section above.

The patterns, as the engine holds them

4 of the 70 rows in our phrase table carry this label. They are printed here as they are written, because a paraphrase of a regular expression is a different regular expression.

/\bin conclusion\b/gi weight 3

Matches “in conclusion” , in any capitalisation .

/\bto summarize\b/gi weight 3

Matches “to summarize” , in any capitalisation .

/\bin summary\b/gi weight 3

Matches “in summary” , in any capitalisation .

/\bto conclude\b/gi weight 3

Matches “to conclude” , in any capitalisation .

What a hit does to your score

The phrase model is one of four in our ensemble, and its formula is patternScore = min(98, max(5, 10 + 7 x total weight)). One occurrence of the heaviest row in this category takes that model from 10 to 31 out of 100 — and the pattern model carries 40% of the ensemble when the em-dash signal fires and 55% when it does not.

Weight 3 rather than 2 because a golden-set regression showed marker-heavy paragraphs scoring only about 45. That is a tuning decision recorded in the engine source, made on a handful of cases.

Check your own text

Our detector is free and shows you which sentences it flagged and why, including this category. It also gets things wrong, and we publish how often.

Run the detector Our measured error rates If you have been accused Which registers score highest

Other things the detector looks for