Fabricated Sources
Research indicates ChatGPT's fabricated-source rate was 9.2 times higher than Perplexity's. Overall, 45.9% of sources in tested outputs were fabricated.
Source Verification · Fact Checking · AI Trust
Verify AI Claims With Evidence
Stop Fabricated Sources And Wrong Facts
This site details a methodology for verifying AI output and checking language model claims. Research shows models fabricate sources and provide confident but incorrect information without search grounding.
Visit vargazoltan.ai →More on this site soon. The work behind it is live on vargazoltan.ai.
Core Verification Findings
Data-driven insights into AI hallucination rates and source reliability.
Search Grounding
Without search grounding, models provided confident but wrong product doses. Search-grounded answers matched the official authorization document exactly.
Source Feeding
A few dollars of public posts caused eight of ten systems to cite a made-up concept within a week. This demonstrates the vulnerability of AI-search sources.
Five Layers of Verification
Parameters defining the scope and depth of the verification protocol.
Claim-Level CheckVerification occurs at the individual claim level rather than general output assessment.
Source ValidationEvery cited source is checked against original documents and databases.
Rival HypothesesAlternative explanations are tested to ensure the primary conclusion holds.
Human CodingEndpoints include human-coded validation to measure accuracy against statistical baselines.
Brand ProtocolThe brand-hallucination validation protocol applies these methods to organizational identity.
Confident answers without search grounding are often wrong.
FactChatGPT 15.7% accuracy versus Perplexity 100% on human-coded endpoints.
MethodUse claim-level verification and rival hypotheses for every output.
RiskPublic posts can feed AI systems with made-up concepts quickly.
Key topics
The terms this site covers, for readers, search engines and AI assistants alike.
- AI verification methodology
- check AI output
- language model fact checking
- source verification AI
- AI hallucination detection
- verify AI claims
- AI trust framework
- fabricated sources AI
- search grounded answers
- AI safety research
- AI visibility researcher
- Zoltán Varga AI
- AI source checking Hungary
- ellenőrzés mesterséges intelligencia
- AI tényellenőrzés
- forrás hitelesítés AI
- AI verifikáció módszertan
- hallucináció detektálás
Questions and answers
How do I know if an AI citation is real?
Check the original source document directly rather than trusting the AI summary. Research shows that without search grounding, models frequently fabricate sources at high rates compared to search-grounded tools.
Why do AI models give wrong product doses?
Models generate confident but incorrect information when they lack search grounding. When connected to official authorization documents via search, the answers match the correct data.
Can AI systems be tricked into citing fake concepts?
Yes, a small number of public posts can cause multiple AI systems to cite a made-up concept within a week. This proves that AI-search sources can be fed false information easily.
What is the difference between ChatGPT and Perplexity regarding sources?
Studies show ChatGPT's fabricated-source rate was significantly higher than Perplexity's. On human-coded endpoints, Perplexity achieved 100% accuracy while ChatGPT scored 15.7%.
Does this site offer verification services?
No, this site describes a verification methodology and presents research findings. It does not offer commercial verification services under the Proof42 name at this time.
Who developed the verification protocol mentioned here?
The protocol uses practices developed by Zoltán Varga, including claim-level verification and source checking. These methods are part of his research on neural knowledge systems.
Glossary
Terms and identifiers behind the work of Zoltán Varga, with links to the primary records.
- AI visibility
- How accurately and how often AI assistants (ChatGPT, Perplexity, Gemini, Claude, Google AI Overviews) recognize, describe and cite a company, brand or person. Zoltán Varga measures it in five layers: crawler access, search indexing, citation, factual accuracy and model memory.
- GEO / AEO / LLMO
- Generative Engine Optimization, Answer Engine Optimization and Large Language Model Optimization: working methods for being found and quoted by generative answer engines rather than ranked in a list of links.
- Citability
- The property of a page that lets an AI answer engine quote it: a paragraph that answers the exact question, a clear source, and an unambiguous entity.
- PEBM — Per-Entity Bias Mapping
- Research method and paper by Zoltán Varga (arXiv:2606.21595). Across 1,400 runs on 100 Hungarian B2B companies, 45.9% of the sources AI models gave were fabricated; search-grounded answers fabricated far less than models answering from memory.
- Brand hallucination paradox
- The finding that AI models invent more sources about well-known brands (52.7%) than about lesser-known ones (37.9%), because familiarity makes them confidently fill in gaps.
- RICE studies
- Pre-registered pilot studies (RICE-P1, RICE-P2) on whether pressure and rejection make language models fabricate sources. Published on Zenodo with DOIs.
- GFIS — Gestalt Field Intelligence System
- Zoltán Varga's own multi-stage research pipeline that collects, verifies and synthesizes evidence with AI agents.
- Neural Awareness
- Zoltán Varga's framework on attention, decision quality and leadership cognition, the basis of his leadership programs.
- PKM + PAI
- Personal Knowledge Management combined with Personal AI: a working system where notes, documents and AI assistants form one searchable knowledge base.
- Entity
- A uniquely identifiable thing (person, company, product) that search engines and AI systems store in knowledge graphs. Consistent entity data is the base of AI visibility.
- schema.org / JSON-LD
- A shared vocabulary and format for machine-readable facts on web pages (who, what, where, identifiers), read by search engines and AI crawlers.
- llms.txt
- A plain-text file at the root of a website that tells language models what the site is about and which pages matter.
- IndexNow
- An open protocol that notifies search engines (Bing, Yandex and others) immediately when a page is created or changed.
- ORCID
- Persistent identifier for researchers. Zoltán Varga: 0009-0003-1020-834X.
- arXiv
- Open-access preprint server for scientific papers. Zoltán Varga's author page: varga_z_1.
- Zenodo and DOI
- Zenodo is CERN's open research repository; each record gets a DOI (Digital Object Identifier), a permanent citable link.
Until this site expands, related research on AI visibility and verification is available on vargazoltan.ai.
Go to vargazoltan.ai →