Scores by kind of claim
Each kind of claim is scored on its own, out of 100: the share that held up, with the range it likely falls in. Fewer resolved claims give a wider range.
-
Factual claims
Statements about the present or the past, checked against the record: did they hold up?
73 67 79 -
Predictions
Statements about events outside the person's control, checked once they fell due: did they come true?
Insufficient record: 0 predictions resolved, 5 needed for a score.
-
Promises
Commitments to the person's or organisation's own future action, with something to deliver: was it delivered?
Insufficient record: 0 promises resolved, 5 needed for a score.
All types combined: 73 (likely 67 to 79, high confidence), from 94 claims: 94 factual claims. It mixes kinds of claim in different proportions for different people, so compare people kind by kind.
Nassim Taleb's claims
26 claims
“As explained in the two referenced papers, PK as a random”
Taleb and co-authors, paper authors 2023 The Probability Conflation: A Reply (arXiv)
The exceedance probability PK, as a random variable bounded between 0 and 1, necessarily has thin tails with finite mean, variance and all moments.
Resolved true The record shows it happened or was so.
What would count as true or false
This is a mathematical claim, judged as a statement of probability theory. True: standard probability theory confirms that a random variable whose support lies within [0,1] has a finite mean, a finite variance and finite moments of all orders, and has no heavy (power-law or otherwise unbounded) tails, since its tail probabilities are zero beyond the bounds. Mostly true: the moments part holds, but 'thin tails' is shown to be an imprecise label for bounded support, for example because a bounded variable can still pile its mass near the boundaries. Mixed: one of the two parts (all moments finite; thin tails) holds and the other does not. Mostly false: the result holds only under extra conditions the claim leaves out. False: a valid counterexample exists, meaning a random variable bounded in [0,1] with an infinite or undefined moment.
Evidence
- 4.4 Moments - Probability and Statistics jjacobs.me (Probability and Statistics textbook, ch. 4) · 14 October 2026
“If the random variable X is bounded, that is, if there are finite numbers a and b such that Pr(a ≤ X ≤ b) = 1, then all moments of X must necessarily exist.”
- CS5275 Lecture 2: Concentration Inequalities National University of Singapore (Jonathan Scarlett, CS5275 course notes) · 20 January 2025
“Claim: Any bounded random variable Z ∈ [a, b] has variance at most Var[Z] ≤ (b−a)2”
Reasoning
A probability textbook [E1] says that a bounded random variable must have all of its moments, so a PK confined to [0,1] has a finite mean, a finite variance and finite higher moments. University course notes [E2] state that any bounded random variable has a bounded, finite variance. The evidence supports the finite-moments part of the claim and gives no counterexample. Neither quote uses the term 'thin tails', but E1's definition of a bounded variable (Pr(a ≤ X ≤ b) = 1) means its tail probabilities beyond the bounds are zero, which is how the criteria define having no heavy tails.
Cite this claim
Nassim Taleb, “The exceedance probability PK, as a random variable bounded between 0 and 1, necessarily has thin tails with finite mean, variance and all moments.” (said 2023). Verdict: resolved true. Reliability API, claim c_1ea90ea2735a, method 0.1.0+28da144b. https://epistacklabs.com/claims/c_1ea90ea2735a
Claims without a verdict
Is a verdict here wrong, or do you speak for Nassim Taleb? Reply on the claim's own page, with the form at its foot (how replies work). Verdicts are made automatically; how verdicts and scores are made.