Diese Seite gibt es auch auf Deutsch.
Auf Deutsch lesen →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 pilotRunning pilots with several Swiss institutions.

Measured in published, peer-reviewed research. What gets through there gets through a submission batch too.
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
176 references GPT-4o produced for mental-health literature reviews, each checked by hand. Every square is one reference.
A plagiarism check flags none of these errors. Fabricated sources are original text.
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%.
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.
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).
Acurio searches the whole source, even when the page reference is off.
In the tutor-supported subgroup, learning outcomes rose by 40%. The full cohort showed no significant difference.
Supported, partly supported, or unsupported, each with its reasoning.
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.”
Surfaces after the grade, if at all.
Caught during review, with the original passage.
Fabricated and overstated citations surface while they are still a correction.
The report shows the flagged passages first. Examiners only read up where it matters.
Every verdict shows the original passage. That holds up before boards and appeals; an AI-detector score doesn’t.
Every thesis is checked the same way, regardless of who supervises it.
In a pilot, we check a real submission batch from your department. Then we walk through the findings together, and you decide. No contract.
We settle scope, file formats, and timing.
Acurio checks real theses against their real sources.
We show you what Acurio found.
Licenses per department, faculty, or institution. Hosted in the EU (Germany), GDPR-compliant, your data is never used for training.
No. Plagiarism software finds copied text. Acurio checks whether the cited source supports the claim. The two complement each other.
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.
For the full check, yes. If a source is missing, Acurio marks the passage “not checked,” never falsely as unsupported.
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.
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.
In the EU (Germany), GDPR-compliant. Uploaded theses and sources never train a model.
Acurio is running pilots with several Swiss institutions. We name them only once the institution agrees.
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.