What Should World Models Forget? Stratified Retention for Continual Adaptation

arXiv 2026 23.8 method, theory

TLDR

This paper argues world models need stratified retention by invariance timescale and proposes differential retention metrics to distinguish correct revision from catastrophic forgetting.

Reasoning

The paper makes a strong conceptual contribution by identifying a gap in continual learning metrics for non-stationary world models. However, it lacks visible experimental validation or real-world benchmarks, and the abstract does not demonstrate the proposed metrics in practice.

Read-first score

Read-first score 23.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 14.

Recency 5%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Reproducibility 15%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=checkpoint,code

Methodology quality 15%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,metric

Topical relevance 25%

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Graph prestige 15%

5.7

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0016

Citation impact 15%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 10%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 104.

Keyword Scores

world model

world dynamics prediction

world simulator

generative world model

interactive world model

video world model

model-based reinforcement learning world model

Resources

Paper