# What a Deletion Certificate Covers, and Where It Expires: Auditable Removal from a Support-Vector Memory

arXiv: https://arxiv.org/abs/2607.12204 · HTML: https://mlsanity.com/paper/2607.12204/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 14 of 14)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [OptNet: Differentiable Optimization as a Layer in Neural Networks](https://mlsanity.com/paper/1703.00443/) (2017)
- [Linear Transformers Are Secretly Fast Weight Programmers](https://mlsanity.com/paper/2102.11174/) (2021)
- [Differentiable Convex Optimization Layers](https://mlsanity.com/paper/1910.12430/) (2019)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [Parallelizing Linear Transformers with the Delta Rule over Sequence Length](https://mlsanity.com/paper/2406.06484/) (2024)
- [Titans: Learning to Memorize at Test Time](https://mlsanity.com/paper/2501.00663/) (2024)
- [Uncovering mesa-optimization algorithms in Transformers](https://mlsanity.com/paper/2309.05858/) (2023)
- [MesaNet: Sequence Modeling by Locally Optimal Test-Time Training](https://mlsanity.com/paper/2506.05233/) (2025)
- [VeriCache: Turning Lossy KV Cache into Lossless LLM Inference](https://mlsanity.com/paper/2605.17613/) (2026)

## Built on by (most cited first, 2 of 2)

- [Can an AI Assistant Really Forget? Auditable Deletion from Addressable Memory](https://mlsanity.com/paper/2607.27539/) (2026)
- [Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate](https://mlsanity.com/paper/2609.06872/) (2026)

## Abstract (arXiv)

We study deletion in a context memory that fits a support-vector boundary around stored keys and uses the resulting nonnegative coefficients to weight their values. An exactly zero coefficient lets us remove a key without changing the current normalized readout. In a three-key construction, however, a later admission makes the discarded key active in a solve over the full history. For a positive-weight key, a decremental update targets a refit on the remaining keys at the original coefficient cap, under its stated assumptions. Earlier standalone comparisons show close typical gate-score agreement, while similar keys with different values can yield larger readout differences. The journal extension tests chained deletions and admissions, checking coefficient feasibility and optimality conditions in both returned states and fresh references. The initial audit completes 66 of 80 trajectories and exposes numerical failures. A separately checked wrapper completes all 5,120 scheduled operations at unchanged acceptance thresholds, with eight initialization rescues and 84 update rescues. Its largest readout difference is 0.5273% of retained-value range. These finite results support explicit acceptance and rescue rules for the evaluated memory edits. They do not extend the current-state removal guarantee to arbitrary future admissions.