SOURCE-LINKED INTELLIGENCE

Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Recurrent, attention-free sequence models share a structural weakness: a fading state cannot perform exact recall of something seen once, far in the past. We add to the Kathleen trunk a second memory layer -- a "notebook": a fixed-key holographic (HRR) associative store with a learned local write gate, a self-gating raw read, and write-triggered forgetting -- 25K parameters that attach to the logits of any trunk. (1) Mechanism: on a controlled needle-in-haystack task the notebook reaches 80-82% one-shot recall at 4x the training length, where the bare trunk scores ~4% and a parameter-matched a

Read original source ↗ Open in workspace

recordType

paper

region

Global