Plagiarism is solved. Citations aren’t.

AI invents references that pass every plagiarism check. Acurio matches each cited claim against the original source, for whole submission batches and before the grade.

Request a pilot

Running pilots with several Swiss institutions.

Acurio review view: a thesis with colour-coded citations and a list of findings

Fabricated sources are multiplying.

Measured in published, peer-reviewed research. What gets through there gets through a submission batch too.

×10Journal articles with a fabricated referenceBiomedicine, 2.47 million articles
Journal articles with a fabricated reference
20231 in 2,828
20251 in 458
Early 20261 in 277

Source: Topaz et al. 2026, The Lancet

×14Conference papers with a fabricated sourceACL, NAACL, and EMNLP
Conference papers with a fabricated source
202420
2025275

Source: HalluCitation Matters 2026

Peer review doesn’t stop them either: at ACL 2026, over 100 already-accepted papers cited literature that doesn’t exist.Source: ACL 2026 Program Chairs

Ask GPT-4o for sources and more than half are wrong.

176 references GPT-4o produced for mental-health literature reviews, each checked by hand. Every square is one reference.

  • 35fabricated outright
  • 64real, but cited with errors
  • 77correct

A plagiarism check flags none of these errors. Fabricated sources are original text.

Source: Linardon et al. 2025, JMIR Mental Health

Even the newest models would rather guess than admit they don’t know.

Artificial Analysis measures how often a model answers wrongly where it should have said “I don’t know.” Among today’s frontier models, that hallucination rate runs from 15 to 95%.

Hallucination rate
DeepSeek V4 Pro (DeepSeek)94.8%
Claude Opus 5.5 (Anthropic)58.6%
GPT-6.1 Sol (OpenAI)54.3%
Kimi K3 (Moonshot AI)53.2%
Grok 4.7 (xAI)29.3%
Qwen3.8 Max (Alibaba)28.8%
Gemini 4 Argon (Google)15.1%
Hallucination rate: Share of wrong answers among all questions a model does not answer correctly. Lower is better. Gemini 4 Argon scores lower because it declines many questions. As of October 3, 2026.Source: Artificial Analysis, AA-Omniscience

Acurio doesn’t ask a model to remember. It reads the source.

For every citation, Acurio finds the matching passage in the original source and judges against that passage. Examiners see claim, source, and reasoning side by side.

  1. 1Capture the claim

    Acurio finds every citation and the claim it is meant to support.

    Digital teaching improves learning outcomes across the board by 40% (Meyer, 2023, p. 24).

  2. 2Find the passage

    Acurio searches the whole source, even when the page reference is off.

    Meyer_2023.pdf · p. 24

    In the tutor-supported subgroup, learning outcomes rose by 40%. The full cohort showed no significant difference.

  3. 3Give a reasoned verdict

    Supported, partly supported, or unsupported, each with its reasoning.

    Partly supported

    The source reports 40% only for the supported subgroup. The thesis generalizes it to everyone.

Fictional example. If a source is missing, the passage reads “not checked,” never “unsupported.”

Before the grade, a fabricated citation is a correction. After it, it’s a case.

  1. Submission
  2. Review
  3. Grade
  4. Archive
Today

Surfaces after the grade, if at all.

With Acurio

Caught during review, with the original passage.

Several Swiss institutions already check with Acurio.

In a pilot, we check a real submission batch from your department. Then we walk through the findings together, and you decide. No contract.

  1. Intro call

    We settle scope, file formats, and timing.

  2. Your batch

    Acurio checks real theses against their real sources.

  3. Review

    We show you what Acurio found.

Request a pilot

Licenses per department, faculty, or institution. Hosted in the EU (Germany), GDPR-compliant, your data is never used for training.

Frequently asked questions

Does Acurio replace our plagiarism check?

No. Plagiarism software finds copied text. Acurio checks whether the cited source supports the claim. The two complement each other.

Is Acurio an AI detector?

No. Acurio doesn’t guess whether a model wrote the text. It shows whether the citation holds, with the original passage as proof. AI as a tool stays allowed; fabricated citations don’t.

Do we need the original sources?

For the full check, yes. If a source is missing, Acurio marks the passage “not checked,” never falsely as unsupported.

Can students use Acurio on their own?

Yes, and that helps you. Students who check first find wrong citations themselves and fix them before the thesis reaches you. A self-check doesn’t make a fabricated source real. A private check doesn’t replace your review, though: you can’t know which version was checked against which sources. The submitted version is what counts, and you check it with Acurio yourself.

Can we see what students check privately?

No. Acurio doesn’t show you or their supervisors what students check with their own account. That lets students check early and fix wrong citations before they submit.

Where does our data live?

In the EU (Germany), GDPR-compliant. Uploaded theses and sources never train a model.

Which institutions are running pilots?

Acurio is running pilots with several Swiss institutions. We name them only once the institution agrees.

Where do the numbers come from?

From The Lancet (2026), JMIR Mental Health (2025), an analysis of the ACL, NAACL, and EMNLP conferences (2026), the ACL 2026 program chairs’ statement, and Artificial Analysis’ AA-Omniscience benchmark. Each chart links its source.