World Embedding Benchmark

arXiv 2026 25.5 benchmark

TLDR

Introduces a benchmark with 8,000 simulated physics videos to evaluate how video embeddings encode physical information, revealing trade-offs and retrieval-augmented generation gains.

Reasoning

The paper contributes a well-designed benchmark and empirical evaluation across multiple tasks, which is a strength. However, it relies on simulated rather than real-world data, and the abstract is truncated, leaving some conclusions incomplete.

Read-first score

Read-first score 25.5, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 20.

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=benchmark,experiment

Reproducibility 15%

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

Topical relevance 25%

28.6

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%

10.9

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0031

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

video world model

generative world model

world dynamics prediction

world simulator

interactive world model

model-based reinforcement learning world model

Resources

Paper