All four detection tools classified 100% of fully human-written papers as true negatives, with false positives nearly absent¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? All four tools classified 100% of human texts correctly as True Negatives (scores between 0 and 20%). → Marijke Van Vlasselaer 2026
Evidence¶
Marijke Van Vlasselaer 2026¶
Marijke Van Vlasselaer, Filip Van Droogenbroeck and Bram Spruyt. (2026). Who wrote this? Evaluating the reliability of AI detection tools in higher education. International Journal for Educational Integrity. https://doi.org/10.1007/s40979-026-00226-w
q2 · i? · design · r2
Classification accuracy analysis of the 40 human-written papers (ground truth = 0% AI) in the synthetic dataset. The article reports all four tools classified "100% of human texts correctly as ‘True Negatives’"; no effect size is printed.
"The results for fully human-written texts show that all four tools classified 100% of human texts correctly as ‘True Negatives’ (receiving a score between 0 and 20%)."
Discussion¶
Related Claims¶
- In a documented exploratory audit, one human-authored manuscript received materially different classifications from five commercial detectors, spanning 0% human to Human Generated — reports the opposite
- AI text detectors can return high AI-detection scores for human-written academic text, raising fairness concerns about authenticity evaluation — reports the opposite
- Independent evaluation found commercial AI-text detectors neither sufficiently accurate nor sufficiently reliable for high-stakes use — reports the opposite
- AI language polishing alone can flip human-authored scholarly texts from human-classified to AI-classified — reports the opposite
- Universities disabling AI detection cite false-positive risk at scale, and detector influence persists in individual grading, journal screening, and institutions without policy revision — related
- Comparative studies report that AI detection tools do not reliably distinguish human-written from AI-generated text — reports the opposite
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
all-tools-accurate-on-human-written-papers |
title |
All four detection tools classified 100% of fully human-written papers as true negatives, with false positives nearly absent |
description |
All four detection tools classified 100% of fully human-written papers as true negatives, with false positives nearly absent |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — marijke-van-vlasselaer-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.