Principia: Relational Physics Tests for Video Models

arXiv 2026 20.9 benchmark

TLDR

Introduces Principia, a benchmark measuring Newtonian physics in video models via calibration-independent relational consistency between paired objects; state-of-the-art generators score low.

Reasoning

Strengths include a clever calibration-independent relational formulation, broad physical phenomena, and real-world controlled scenes that expose failures despite high VBench scores. Weaknesses include limited methodological detail in the abstract and minimal discussion of evaluation limitations or comparison to prior benchmarks.

Read-first score

Read-first score 20.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 17.

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

Reproducibility 15%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Topical relevance 25%

24.3

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

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: 105.

Keyword Scores

video world model

world dynamics prediction

world model

world simulator

generative world model

interactive world model

model-based reinforcement learning world model

Resources

Paper