Scores, badges, and verdicts on this platform come from a documented, repeatable process. Here is what we do — and what we do not do.
For the system overview, analysis pipeline, and current limitations, see the about page.
Factual claims are extracted from each article. The subset that references our supported data categories — US CPI, US unemployment, GDP, or inflation — is cross-referenced against BLS and World Bank data. A claim is only marked Confirmed if corroborating evidence exists from at least two independent sources; most claims fall outside this narrow window and are honestly labeled unverifiable.
Our AI reads the article and identifies discrete factual claims — statements that can be tested against data.
Each claim is matched against a narrow set of authoritative economic data: US Bureau of Labor Statistics CPI and unemployment figures, plus World Bank GDP and inflation figures. Claims outside this scope cannot currently be cross-checked and are marked unverifiable.
Confirmed = supported by ≥2 independent sources. Contradicted = primary evidence directly contradicts the claim. Unconfirmed = insufficient public data to confirm or deny.
The Source score reflects the outlet's historical accuracy — not the quality of this specific article. It is calculated from the outlet's track record across all articles we have processed.
How often the outlet has issued corrections or retractions relative to total article volume
Percentage of verifiable claims in past articles that checked out against authoritative sources
How many distinct source categories (government, academic, industry, NGO) are cited per article on average
The Manipulation score (0–100, lower is better) measures how much an article relies on emotional triggers rather than facts. It is a weighted composite of several detected signals; the exact weighting is not published so the system is harder to game.
Flags emotionally charged words and phrases — fear, outrage, and urgency triggers — relative to the rest of the article.
Measures the sentiment gap between the headline and the article body. A strongly negative headline paired with a more neutral body scores high.
Detects passive voice used to obscure agency, selective quoting of only one side, and adjective-to-noun ratios above editorial norms.
Bias detection does not label outlets as “left” or “right.” It identifies specific structural patterns in how a story is told. Four categories are tracked.
How an event is characterized — word choices that assign blame, credit, or urgency without stating facts. Example: "regime" vs "government", "crisis" vs "situation".
Factual information present in other sources covering the same event that is absent from this article. Detected by cross-referencing coverage.
Exaggeration of stakes, certainty, or urgency beyond what the evidence supports. Overlaps with manipulation detection.
Over-reliance on a single category of sources (e.g. all US government, all financial media). Diversity of perspective is tracked per article.
We do not investigate or publish original fact-checks. We cross-reference claims against existing authoritative data and publicly available sources.
Source scores are a measured track record, not editorial judgments. A 78% score means 78% of the outlet’s verified claims have checked out so far, out of a limited sample — it is not a guarantee about any single article.
Claim extraction and stance detection are probabilistic. Every verdict should be treated as an analytical signal, not a definitive ruling. Source links are always provided so you can check yourself.
The trust-tier thresholds in our scoring code apply uniformly to every source’s claim history — we do not special-case specific outlets. Any outlet can contact us to dispute a specific verdict with evidence.