Both detectors performed poorly on hybrid human–AI texts, with Originality showing near-zero recall for the Hybrid class¶
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? Both Turnitin and Originality performed poorly on Hybrid texts; Originality's recall for the Hybrid class was 0.02, near zero. → Mohammad Hadra 2026
Evidence¶
Mohammad Hadra 2026¶
Mohammad Hadra, Karleen Cambridge and Mostefa Mesbah. (2026). Evaluating the accuracy and reliability of AI content detectors in academic contexts. International Journal for Educational Integrity. https://doi.org/10.1007/s40979-026-00213-1
q2 · i? · design · r2
Per-class results from the confusion-matrix analysis of the 192-text evaluation (Table 1) show Turnitin Hybrid sensitivity 0.31 and Originality Hybrid sensitivity 0.02; the article states "Performance on Hybrid texts was weak across all metrics". Hybrid texts were constructed with approximately 50% human and 50% AI content.
"Performance on Hybrid texts was weak across all metrics, reflecting a limited ability to detect mixed authorship."
Discussion¶
Related Claims¶
- Originality outperformed Turnitin in overall accuracy and macro-average recall on a balanced EFL-relevant dataset, but both showed limited consistency across classes — related
- Independent evaluation found commercial AI-text detectors neither sufficiently accurate nor sufficiently reliable for high-stakes use — a broader claim this one bears on
- Originality showed a borderline non-significant trend toward higher accuracy on professional than EFL student writing, while Turnitin showed no significant difference — related
- Hybridization of authorship blends human and AI-generated content, often without learners' explicit awareness of the boundary, normalizing formulaic rhetorical structures — related
- Both detectors achieved substantially lower accuracy on scientific writing than on humanities texts — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
detectors-fail-hybrid-authorship-texts |
title |
Both detectors performed poorly on hybrid human–AI texts, with Originality showing near-zero recall for the Hybrid class |
description |
Both detectors performed poorly on hybrid human–AI texts, with Originality showing near-zero recall for the Hybrid class |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — mohammad-hadra-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.