Facts receive scores.
A checkable claim describes something that could be supported or contradicted by evidence: an event, quotation, measurement, date, amount, cause, or documented action.
FakeNewsZero.com measures how strongly the available evidence supports a factual claim. The score is a structured summary of evidence—not the probability that a statement is true.
Every result follows the same path: decide what can be checked, break it into parts, examine the evidence, combine the scores, and apply limits where confidence would otherwise be overstated.
Strong, direct, independently corroborated evidence.
Good evidence with limited remaining uncertainty.
Some support, but an important gap remains.
The available evidence is too limited or mixed.
Key parts are unsupported, distorted, or contradicted.
Reliable evidence directly conflicts with the claim.
A checkable claim describes something that could be supported or contradicted by evidence: an event, quotation, measurement, date, amount, cause, or documented action.
Personal judgments such as “this person is unintelligent” are not scored as true or false. If a statement mixes opinion with factual premises, only the factual parts are checked.
For phrases such as “someone said,” the user chooses whether to check the words themselves or whether a named person or source actually said them.
A sentence can contain several independently testable ideas. The system separates the core assertion from dates, quantities, causes, locations, groups, and attributions. Each part must be able to stand or fail on its own.
Did Stanford publish or conduct the cited study?
Was the study published in 2025?
Did the study examine high-school students?
Did students sleeping at least eight hours score 20% higher on math tests?
Does the evidence show that improved memory caused the score difference?
Each atomic claim receives a score from 0 to 100. The assessment considers:
Each part receives a percentage representing how much it matters to the statement as a whole. The weights always total 100%, and the core claim receives the largest share.
A small date error should not automatically erase a well-supported central claim. A failed core claim should matter much more than a minor detail.
Combines the independently scored parts according to their importance.
Combines the weighted claim score with O, an overall assessment of the evidence as a complete picture.
Using both views reduces the chance that one unusually strong or weak subscore controls the entire result.
This hypothetical example shows the arithmetic. It is not a live fact-check.
A claim cannot receive a confident score without reviewable evidence.
One credible source can be useful, but it is not independent corroboration.
Evidence may support a forecast, but the event has not happened yet.
The system explains why the statement cannot be verified as a factual claim.
The score is only as good as the evidence available at the time of the search. Sources can be incomplete, new information can emerge, and automated analysis can make mistakes. A high score is not a guarantee; a low score does not prove intent to deceive.
Every result therefore shows its claim breakdown and sources. The number is the beginning of the explanation, not the end of it.