topic

Min-IP

Narrative intelligence for Min-IP: 1 tracked articles, claims, and spin patterns across AI and technology coverage.

Three Tokens Force Exponential Feature Rank in Nonnegative Kernel Attention

A theoretical machine learning paper proves exponential feature growth is necessary for nonnegative kernel attention to handle three-token sequences under Min-IP on Boolean inputs — revealing a fundamental expressivity gap versus full attention.

Spin 40% Claim Present in Source AI Risk Moderate

arXiv Machine Learning

Aug 13, 2026

Related Claims

01 Any single normalized nonnegative kernel-attention head that succeeds on all three-token sequences with error strictly below $1/2$ requires $2^{\Omega(m)}$ features, even with arbitrary finite-dimensional tokenwise values and an arbitrary query-dependent affine readout.

Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO