mlsanityData to 7 Oct 2026

Holographic Invariant Storage: Design-Time Safety Contracts via Vector Symbolic Architectures

arXiv 2603.13558 ↗First posted 13 Mar 2026stat.ML cs.CL cs.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce Holographic Invariant Storage (HIS), a protocol that assembles known properties of bipolar Vector Symbolic Architectures into a design-time safety contract for LLM context-drift mitigation. The contract provides three closed-form guarantees evaluable before deployment: single-signal recovery fidelity converging to 1/√2 ≈ 0.707 (regardless of noise depth or content), continuous-noise robustness 2Phi(1/σ) - 1, and multi-signal capacity degradation ≈√1/(K+1). These bounds, validated by Monte Carlo simulation (n = 1,000), enable a systems engineer to budget recovery fidelity and codebook capacity at design time -- a property no timer or embedding-distance metric provides. A pilot behavioral experiment (four LLMs, 2B--7B, 720 trials) confirms that safety re-injection improves adherence at the 2B scale; full results are in an appendix.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 13 Mar 2026.

Builds on

20 of 33 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  9. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  10. 2016Concrete Problems in AI Safetycited by 1,582
  11. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  12. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
8 more
  1. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  2. 2022Red Teaming Language Models with Language Modelscited by 983
  3. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  4. 2014Neural Turing Machinescited by 630
  5. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 347
  6. 2022Memorizing Transformerscited by 219
  7. 2020A comparison of Vector Symbolic Architecturescited by 63
  8. 2020A Theoretical Perspective on Hyperdimensional Computingcited by 43

Built on by

Not cited yet.