arXiv (All)
open access
Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value Algebras
We identify a recurrent algebraic regularity in Transformer attention: a sparse subset of effective OV operators $T=OV^\top$ nearly closes under composition, $T^2\approxαT$. Across six pretrained endpoints spanning 2.8B--235B parameters, 3.98--8.00% of heads reach squared closure alignment $\mathcal
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Shift-Accumulate Attention: Multiplier-Free Query--Key Products for Transformer Decoding#986979
- Semi-analytical results for $e^+e^-\to J/ψ+ X_{{\rm non\,}c\bar{c}}$ up to $\mathcal{O}(α_s v^2)$ at B factories#987711
- Correspondences, motifs and monoidal transformations#490283
- Perplexity and Philosophical Progress#75374
- Hahn-Type Orthogonality for the Resolvent Delta Operator $\mathscr L=D(I-D)^{-1}$#1115761
Record · ID 821101
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive