System Architecture

Declassified overview of the TruthCheck verification pipeline.

01

Claim Extraction

The system first analyzes your input text using spaCy to identify factual claims. It filters out questions, opinions, and personal statements, isolating only verifiable assertions about the real world.

02

Evidence Retrieval

Using extracted keywords, TruthCheck scrapes trusted sources (Wikipedia, Government domains, Scientific Journals) via standard search protocols. It specifically prioritizes high-credibility domains like .gov, .edu, and reuters.com.

03

NLI Classification

The core "brain" uses Large Language Models (RoBERTa & DeBERTa) fine-tuned for Natural Language Inference (NLI). It compares the claim against each piece of evidence to determine if the evidence Entails (supports), Contradicts (refutes), or is Neutral towards the claim.

04

Consensus Voting

Finally, all model judgments are aggregated using a weighted voting mechanism. Sources with higher domain authority carry more weight. The system calculates a final confidence score and issues a verdict: TRUE, FALSE, or LOW CONFIDENCE.