OpenAI preprint, September 2026 · §2. The scalar rate and its curvature
Lemma2.1:The entropy deficit has a positive power series on the full interval of biases
Quadratic bounds for binary entropy.
Hover over a blue or green term in the text, or a node in the graph, to find it in the other. Select it to read its
declaration both in Lean and in words.
The Setting
For a binary coordinate of bias , the entropy deficit measures the shortfall from the entropy of an unbiased bit. Its comparison with gives quadratic control of the entropy as the bias varies.
The constant is the natural logarithm of :(1)✦
The binary entropy deficit is defined by (2), with :(2) The binary entropy in nats is defined by (3): (3)
The deficit coefficients , for integers , are the positive real numbers in (4): (4)✦
The Claim
Theorem 1. Let satisfy . Then (5)✦(6)✦(7)✦ The following series converge to the indicated values: (8)✦(9)✦
In the paper, the result reads: for , and , the quotient is strictly increasing on , and and .
What Is Checked
The bounds (5), (6) and (7) and the series identity (8) are stated over real biases with their entropy and deficit, while (9) concerns the real coefficient sequence.