A² — Assay · Beyond Detection

Integrity is about substance, not style.

The question is not who typed the words. It is whether what they assert can be traced to evidence.

Three generations of integrity checking

Assay moves the question from authorship to evidence.

Generation 1

Similarity checking

Compares text against other text. Finds copying, but not whether anything is true.

Asks: has this been written before?
Generation 2

“AI detection”

Guesses at authorship from style. It cannot see inside an assertion and penalises honest writers.

Asks: who, or what, wrote this?
Generation 3 · Assay

Claim verification

Decomposes writing into claims and traces each one to evidence. Integrity becomes a question of substance.

Asks: is what this says true?

What fluent writing hides

Four failure modes that stylistic checks cannot see.

Surface fluency

A paragraph that reads like scholarship but is hollow at its factual core.

Fabricated citations

Authors, journals and references that sound right but do not exist.

Statistical distortion

Findings stretched, compressed or invented behind confident prose.

Retracted re-citation

Withdrawn studies cited for years after they were retracted.

Why detection falls short

Generative systems write with remarkable fluency and authority, yet have no intrinsic concept of truth. Tools that guess at authorship from style cannot see inside an assertion. They miss confident falsehoods and can unfairly flag honest writers.

Assay treats this as a question of epistemic governance rather than style. It checks what is claimed, so it remains useful however a document was produced.

Join the Assay pilot

Available through our Pilot Access programme for selected institutional partners.