MOSS detected far fewer suspicious cases in Spring 2026 than in prior offerings, as LLM-assisted submissions lack similarity signals¶
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? In Spring 2026, MOSS flagged an average of about 2-3 suspicious student-to-student plagiarism cases per assignment, a significant decrease from prior offerings. → David Racovan 2026
Evidence¶
David Racovan 2026¶
David Racovan, Ajay Rawat, Christopher K. May, Jeffrey A. Turkstra. (2026). Argus: Academic Integrity in the Era of Generative AI. https://arxiv.org/abs/2609.36073 doi:10.48550/arxiv.2609.36073
q2 · i? · design · r2
Parallel use of the similarity-based MOSS tool during the Spring 2026 offering; the article reports "an average of about 2-3 suspicious student-to-student plagiarism cases per assignment". No statistical test or effect size is printed for the decrease.
"We also utilized MOSS in parallel withArgus for the Spring 2026 offering, but detected cases were significantly decreased compared to prior offerings, with an average of about 2-3 suspicious student-to-student plagiarism cases per assignment."
Discussion¶
Related Claims¶
- In Spring 2026, 45.7% of students in a large CS2 course were flagged as LLM-assisted following structured manual review — related
- Flagged Spring 2026 students scored lower on all three exams than non-flagged peers, with performance declining as flagged assignments increased — related
- Average H-scores rose from near-zero in pre-LLM offerings to 11.9 in Spring 2026, with maximum scores reaching 81 — related
- In an unrestricted university course, only a minority of students (23 of 68, 34%) reported using LLMs, averaging 12% of discussion-point and 11% of critical-summary submissions — related
- The visualizer's flagging mechanisms flagged all tested logs from cases already known to involve plagiarism while still requiring student-level review — related
- Popular plagiarism detection tools detect plagiarism in AI-assisted essays in less than 15% of cases — related
- On fully AI-generated papers produced with ChatGPT Deep Research, Pangram achieved 65% strict accuracy while Turnitin, GPTZero and Copyleaks classified essentially all papers as false negatives — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
moss-detection-declined-spring-2026 |
title |
MOSS detected far fewer suspicious cases in Spring 2026 than in prior offerings, as LLM-assisted submissions lack similarity signals |
description |
MOSS detected far fewer suspicious cases in Spring 2026 than in prior offerings, as LLM-assisted submissions lack similarity signals |
status |
review |
evidence_strength |
weak |
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 — david-racovan-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.