OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

arXiv 2023 38.9 benchmark, system

TLDR

A benchmark for spatio-temporal predictive learning, comparing recurrent and recurrent-free models across multiple domains.

Reasoning

The paper provides a standardized evaluation framework and extensive datasets, which is a strength for reproducibility. However, it lacks novel model contributions and the core focus is benchmarking rather than advancing world model theory.

Read-first score

Read-first score 38.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 10.

Recency 8%

65.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2023

Methodology quality 25%

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

Reproducibility 25%

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

Topical relevance 42%

14.3

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

Field roles

Candidate

Rank sensitivity

Stability: volatile; rank range: 90.

Keyword Scores

world model

video world model

world dynamics prediction

world simulator

generative world model

interactive world model

model-based reinforcement learning world model

Resources

Paper