OpenAI preprint, September 2026 · §2. The scalar rate and its curvature
Lemma2.4:An upper bound in the open entropy interval and a separate value at zero
Entropy weights control scalar rate curvature.
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
Binary information on the discrete cube gives a scalar rate parametrized by the entropy deficit of a binary bias. A bias describes a sign with probabilities and .
The binary entropy deficit is the function of the bias in (1), with natural logarithms and the usual entropy convention :(1)The inverse entropy deficit is the inverse of restricted to : for , its value is the unique bias in that interval with entropy deficit .✦
The scalar rate is the function on defined parametrically by (2): (2) The profile curvature is a real function of the entropy-deficit argument , equal to for and to the expression in (3) for , where :(3)
The complementary entropy coordinate associated with a deficit is the real number specified by .The correction curvature is the function of the real entropy coordinate defined by (4): (4)✦
The Claim
Theorem 1. For an entropy coordinate with ,(5)✦For a deficit with ,(6)✦The endpoint value is (7)✦For every positive entropy coordinate ,(8)✦
In the paper, the result reads: for , put ; then , with .
What Is Checked
The statements (5), (6) and (7) concern the profile curvature defined from the inverse binary entropy deficit on the open physical interval and at zero, while (8) concerns the piecewise correction curvature on the positive entropy axis.