Phase Structure in Rotary Attention: A Spectral Framework for Semantic Continuity and Execution-Boundary Governance

arXiv:2607.25507 · cs.CL · Submitted 2026-07-28 · Read on arXiv

cs.CL

Submitted: 2026-07-28

Updated: 2026-09-09

Comments: 14 pages; theoretical framework and proposed experimental program

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 16× in this paper · explained in 1 episode
• Transformer — 15× in this paper · explained in 2 episodes
• Admissibility — 11× in this paper · explained in 2 episodes
• Interpretability — 4× in this paper · explained in 15 episodes
• Semantic Drift — 3× in this paper · explained in 3 episodes
• Active Governance — 2× in this paper · explained in 1 episode
• Alternation — 2× in this paper · explained in 1 episode
• Mechanistic interpretability — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Continuity Governance Mesh — 1× in this paper
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes
• Wavelet Transform — 1× in this paper · explained in 2 episodes

Sources

• Attention Is All You Need
• Similarity of Neural Network Representations Revisited
• In-context Learning and Induction Heads
• Round and Round We Go! What makes Rotary Positional Encodings useful?
• Deconstructing Positional Information: From Attention Logits to Training Biases
• Rotary Positional Embeddings as Phase Modulation: Theoretical Bounds on the RoPE Base for Long-Context Transformers

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering