As video diffusion models (VDMs) advance toward world models, a key question arises: do they truly understand causality, or merely overfit to statistical temporal patterns? Existing benchmarks mostly rely on synthetic data, limiting real-world generalization due to the sim-to-real gap. We present YoCausal, a two-level benchmark inspired by the Violation of Expectation (VoE) paradigm from cognitive science. By temporally reversing real-world videos at zero cost as natural counterfactual samples, YoCausal establishes an arbitrarily extensible evaluation protocol. Level 1 introduces the Reverse Surprise Index (RSI), quantifying arrow-of-time perception via denoising loss. Level 2 introduces the Causality Cognition Index (CCI), which leverages a VLM to stratify datasets into causal and non-causal subsets, disentangling genuine causal reasoning from temporal bias. Evaluation of 13 state-of-the-art VDMs reveals that perceiving the arrow of time does not imply understanding causality, and a significant gap persists relative to human-level causal cognition.

翻译：随着视频扩散模型（VDM）向世界模型迈进，一个关键问题浮现：它们是否真正理解因果性，抑或仅仅过拟合了统计性的时间模式？现有基准大多依赖合成数据，由于仿真-现实差距限制了现实世界的泛化能力。我们提出YoCausal，这是一个受认知科学中期望违背范式（VoE）启发的双层基准。通过零成本地将真实世界视频时间反转作为自然反事实样本，YoCausal建立了一种可任意扩展的评估协议。第一层引入反向惊讶指数（RSI），通过去噪损失量化时间箭头感知。第二层引入因果认知指数（CCI），利用视觉语言模型（VLM）将数据集分层为因果子集和非因果子集，将真正的因果推理从时间偏差中分离出来。对13个最先进VDM的评估揭示：感知时间箭头并不意味着理解因果性，且与人类水平的因果认知相比仍存在显著差距。