# Diagnosing Capability Preservation and Task Sensitivity in Memory Augmented Document Classifiers

arXiv: https://arxiv.org/abs/2512.06582 · HTML: https://mlsanity.com/paper/2512.06582/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 6 Dec 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [Linear Transformers Are Secretly Fast Weight Programmers](https://mlsanity.com/paper/2102.11174/) (2021)
- [Hopfield Networks is All You Need](https://mlsanity.com/paper/2008.02217/) (2020)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?](https://mlsanity.com/paper/2005.00719/) (2020)
- [Continual Pre-Training Mitigates Forgetting in Language and Vision](https://mlsanity.com/paper/2205.09357/) (2022)
- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [SMEMO: Social Memory for Trajectory Forecasting](https://mlsanity.com/paper/2203.12446/) (2022)
- [Neural Learning Rules from Associative Networks Theory](https://mlsanity.com/paper/2503.19922/) (2025)

## Abstract (arXiv)

End task accuracy alone cannot determine whether a memory mechanism preserves an acquired capability, exposes sample-specific stored information, or contributes measurably to downstream performance. This study introduces Protected QL Memory and evaluates capability preservation, diagnostic access, and task performance sensitivity as distinct empirical properties. Protected QL Memory is a dual path document classifier combining a causal local pathway, an associative matrix writer, and a finalized memory reader. A capability-protected schedule acquires a controlled binding capability, adapts the local pathway while constraining writer degradation, trains controlled memory access, and restricts full path task fitting. Pre and post adaptation diagnostics and finalized-memory interventions were evaluated across nine dataset-seed conditions. Writer capability was fully preserved, with 100% post-adaptation accuracy. Cyclic reassignment of finalized matrices produced diagnostic accuracy gaps of 86.3 to 86.9 percentage points, showing strong dependence on example memory correspondence. In contrast, natural text macro F1 changed by less than 0.002 when finalized matrices were reassigned, zeroed, or replaced by batch means. Locked-test macro F1 was 90.94% on AG News, 81.78% on IMDB, and 62.63% on Yelp Review Full, comparable to compact controls. Preserving associative capability and maintaining diagnostic access to sample specific memory did not imply measurable downstream reliance on that memory. Protected memory designs should therefore treat capability preservation, diagnostic access, and task alignment as separate objectives and evaluate downstream memory sensitivity directly.