SOURCE-LINKED INTELLIGENCE

Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structure

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Standard positional encodings represent position as a one-dimensional reading-order coordinate, but reading order alone does not determine hierarchical textual structure. We use a hierarchical rotary positional encoding (hRoPE) that represents paragraph, sentence, and token indices as separate channels, hold the token sequence fixed, intervene on the paragraph coordinate p1, and measure cross-paragraph attention with a token-distance-exact estimator. Attention is compressed relative to a token-distance-matched baseline in every corpus, but compression alone is not diagnostic of true structure:

Read original source ↗ Open in workspace

recordType

paper

region

Global