{"ID":5438813,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T11:04:44.15433009Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31495","arxiv_id":"2606.31495","title":"Surprise as a Signal for Plasticity and Metacognition","abstract":"We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition. In the first system, a non-parametric episodic memory writes a new concept only when this surprise is high, and a periodic offline replay phase consolidates recent traces into a slow linear readout. On a continual stream of 1000 ImageNet classes with a frozen DINOv2 or I-JEPA backbone, the consolidation phase recovers 17.7 points of retention on the oldest classes for DINOv2 and 51.3 points for I-JEPA (single-seed runs), and an ablation shows that replaying only a recent window is worse than no replay at all. In few-shot evaluation the same memory reaches 91.6% on 5-way 1-shot mini-ImageNet, above a task-specific baseline, while a harder 500-way regime exposes the true difficulty. In the second system, the same surprise signal, computed in a shared text-image space, modulates the behaviour of a vision-language model: it answers assertively when a concept is known, hedges when it is partially familiar, and refuses to identify the object and asks for an explanation when it is novel, learning the concept from a single user utterance. The external detector separates known from novel concepts at an AUROC of 0.966 (95% CI +/-0.024), far above the model's own verbalised confidence (0.618), while its token-level confidence sits below chance under greedy decoding; after a sleep phase that empties the fast store, the system recalls 99.2% of fifty taught facts from the consolidated store while a base model recovers none. We report both systems as proof-of-concept, with explicit limitations, and position the second against recent episodic-memory and personalised-VLM work.","short_abstract":"We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition. In the first system, a non-parametric episodic memory writes a new concept only when this surp...","url_abs":"https://arxiv.org/abs/2606.31495","url_pdf":"https://arxiv.org/pdf/2606.31495v1","authors":"[\"Louis Mouchon\"]","published":"2026-06-30T11:14:04Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}