Learning Chaos Without Seeing Chaos: Extrapolation of Global Dynamics in Autoregressive Transformers

arXiv 2026 21.5 method

TLDR

Small autoregressive transformers trained on restricted parameter trajectories of nonlinear systems can extrapolate to chaos and period-doubling cascades with high numerical fidelity.

Reasoning

The paper presents compelling evidence that local training data can yield global dynamical extrapolation, supported by quantitative results like the Feigenbaum constant and causal attention analysis. However, all evaluations are on synthetic dynamical systems, and the paper does not address more general world modeling, real-world data, or interactive/R L settings.

Read-first score

Read-first score 21.5, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 11.

Recency 5%

100

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

Methodology quality 15%

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

Reproducibility 15%

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

Topical relevance 25%

15.7

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: 75.

Keyword Scores

world dynamics prediction

world model

world simulator

generative world model

interactive world model

video world model

model-based reinforcement learning world model

Resources

Paper