Metraipolis › archive › dc_df36f6d34dae
What Should World Models Forget? Stratified Retention for Continual Adaptation — arXiv:2610.03713
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03713
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:50:48.936Z
- SHA-256 of the archived text
ffc8118ffe045d8f2e22a384ecc151afb6732b72f1926266a7dcf8a09fcb4328- Stable URL of this page
https://metraipolis.com/documento/dc_df36f6d34dae
How to cite
What Should World Models Forget? Stratified Retention for Continual Adaptation — arXiv:2610.03713 — arXiv, https://arxiv.org/abs/2610.03713 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df36f6d34dae (Metraipolis archive dc_df36f6d34dae, sha256 ffc8118ffe045d8f2e22a384ecc151afb6732b72f1926266a7dcf8a09fcb4328)
BibTeX
@misc{dcdf36f6d34dae,
title = {What Should World Models Forget? Stratified Retention for Continual Adaptation — arXiv:2610.03713},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03713},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df36f6d34dae; sha256 ffc8118ffe045d8f2e22a384ecc151afb6732b72f1926266a7dcf8a09fcb4328},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03713. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a correct label remains correct indefinitely. World models do not satisfy this condition. Their prediction target is the environment, which changes, so knowledge that was accurate when acquired may later become false, and discarding it is required behavior rather than a defect. Non-stationary ground truth is well studied in the concept drift literature and in the temporal factuality of language models, but has not been formulated for world models, which are distinctive in that they also encode knowledge that must never be revised. We argue that continual world models require retention stratified by invariance timescale, separating invariants such as physics and object permanence, which must never be revised, from instance-level facts that should be revised as soon as the environment changes. Standard forgetting metrics cannot distinguish a world model that has correctly revised outdated knowledge from one that has suffered catastrophic forgetting, and consequently rank a frozen model highest, while existing physical-reasoning benchmarks evaluate only frozen checkpoints. We propose differential retention, which reports invariant regression testing across the adaptation stream jointly with revision latency, without aggregation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV); Signal Processing (eess.SP). Pagina del lavoro: https://arxiv.org/abs/2610.03713 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-05T22:45:55.884Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).