← Mathematical compendium

Published equation contexts

pk=1−(1−p)kp_k = 1 - (1-p)^k

Why this formula appears here

There is a simple reason a single successful transfer matters more than its raw success rate suggests. If one crafted probe defeats a given safety-trained policy with probability p , and successive attempts against it were independent, the probability that at least one of k attempts succeeds is pk=1−(1−p)kp_k = 1 - (1-p)^k. which climbs quickly even when p is small per attempt. Two caveats matter as much as the formula. Attempts against one fixed, deployed model are usually correlated rather than independent, so real gains from repeated probing fall below this bound; and a universal, transferable suffix is close to the case the formula flatters most, because it is a single artefact effective across…

Read the full article-specific guide →

Read the representative guide

How to interpret it

Read it with the definitions, units, and assumptions supplied by the article.

Research cited beside this formula

Published contexts (3)

A symbol can carry a different meaning in another article. Each occurrence keeps its own guide and term definitions.

pk=1−(1−p)k,p_k = 1 - (1-p)^k,

Equation 3 · Model Evaluation

Two Different Bets on How to Align a Frontier Model

This equation states an equality: the expressions on both sides have the same value under the article’s assumptions.

There is a simple reason a single successful transfer matters more than its raw success rate suggests. If one crafted probe defeats a given safety-trained policy with probability p , and successive attempts against it were independent, the probability that at least one of k attempts succeeds is pk=1−(1−p)kp_k = 1 - (1-p)^k. which climbs quickly even when p is small per attempt. Two caveats matter as much as the formula. Attempts against one fixed, deployed model are usually correlated rather than independent, so real gains from repeated probing fall below this bound; and a universal, transferable suffix is close to the case the formula flatters most, because it is a single artefact effective across…

Meanings in this article

  • pkp_k: the probability that at least one of k attempts succeeds.
  • pp: the probability.
Equation guide → · Article →
pk=1−(1−p)k,p_k = 1 - (1-p)^k,

Equation 3 · Model Evaluation

OpenAI and Claude on Formal Reasoning: What the Benchmarks Show, and Where They Mislead

This equation states an equality: the expressions on both sides have the same value under the article’s assumptions.

Consider what the o1 numbers alone expose about how these gains are produced. If a single attempt at a problem succeeds with probability p , and k attempts were independent, the probability that at least one succeeds is pk=1−(1−p)kp_k = 1 - (1-p)^k. a curve that climbs fast and then saturates. It is tempting to read o1’s jump from 74% (one sample) to 83% (64-sample consensus) to 93% (1,000-sample rerank) as roughly this shape. It is not, for two reasons that matter for how the number should be read. First, repeated attempts by one model on one problem are correlated — the same misconception that causes one failure tends to recur — so the realised gain from added samples falls well below what…

Meanings in this article

  • pkp_k: the probability that at least one succeeds.
  • pp: the probability.
Equation guide → · Article →
pk=1−(1−p)k,p_k = 1 - (1-p)^k,

Equation 27 · Foundation Models

OpenAI Model Systems from First Principles: Weights, Post-Training, and Inference Compute

This equation states an equality: the expressions on both sides have the same value under the article’s assumptions.

The parallel-sampling case makes the shape of the returns explicit. If a single attempt succeeds with probability p and attempts were independent, the probability that at least one of k succeeds is pk=1−(1−p)kp_k = 1 - (1-p)^k. which is concave in k and saturates quickly. Two caveats destroy any naive extrapolation from it. Attempts from one model on one prompt are strongly correlated, so realised gains fall well below this bound; and pkp_k is only achievable if something can identify the successful attempt. Without a verifier, extra samples buy candidates, not answers. This is precisely why the reasoning-effort control and the availability of parallel test-time compute are architectural facts about a…

Meanings in this article

  • pkp_k: only achievable if something can identify the successful attempt.
  • pp: the probability.
Equation guide → · Article →