Holographic Invariant Storage: Design-Time Safety Contracts via Vector Symbolic Architectures
stat.ML, cs.CL, cs.IT, cs.LG, math.IT
Submitted: 2026-03-13
Updated: 2026-08-24
Comments: The experiment has a design defect: the VSA drift trigger was not in the causal path of its own runs, so the results do not test the claimed mechanism. Clean-room replication: content-aware re-injection beats neither random re-injection (p=0.46) nor a fixed timer (p=0.29), while positive controls confirm task signal (p=0.002, p=0.001). The conclusions are unsupported and should not be cited
Code: https://github.com/Belverith/Aetheris-Research
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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
Terminology
Abstract
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/sqrt 2 about 0.707 (regardless of noise depth or content), continuous-noise robustness 2Φ(1/σ) - 1, and multi-signal capacity degradation about sqrt 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.
Sources
- Concrete Problems in AI Safety
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Constitutional AI: Harmlessness from AI Feedback
- Show Your Work: Scratchpads for Intermediate Computation with Language Models
- Neural Turing Machines
- Steering Language Models With Activation Engineering
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey