- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper addresses the failure of video world models to distinguish observation from intervention under confounding. It proposes Causal Markov Supervision (CMS), a post-training procedure that injects a user-specified causal DAG into a pretrained video world model. The intuition is that the DAG’s Markov property specifies which history is irrelevant given the evidence. Penalizing disagreement between paired predictions that differ only in such history therefore teaches the model what not to attend to. In a single synthetic Unity environment, the arms trained with intervention data estimate the target intervention outcome reasonably well with little loss in visual fidelity. However, the Markov loss itself does not improve the primary metrics, and the full CMS model recovers causal structure worst among all arms.
Critical strengths
- Well-motivated problem and novel formulation: The DAG-forward workflow and the use of paired-prediction JSD to enforce DAG-implied conditional independences offer a simple way to inject causal inductive bias into a video world model.
- Targeted evaluation design: The setting where observational and interventional contrasts have opposite signs directly tests whether a model conflates P(R | do(X), A) with P(R | X, A).
- Practical trace labeling: GPT-5.6 Terra labels 99.3% of event values correctly which suggests that DAG traces can be obtained without manual annotation.
Critical weaknesses
- Markov supervision does not help: Adding the Markov loss increases Δγ̂₁ from .125 to .196 without interventions and from .003 to .063 with interventions (Table 4).
- Claims contradicted by results: The claim that “CMS recovers causal structure” conflicts with Table 4 where CMS has the worst SID (44) and d-separation F1 (.320).
- No evidence that standard training fails: The paper reports no baseline that produces the wrong-sign contrast on the do(X) query even though the abstract states that confounding causes “standard world-model training to fail on the causal effect”.
- Trace–video inconsistency: Generated traces agree with the generated videos on only 35–61% of outcome values (vs. 99.7% on simulator video) which undermines the claim that CMS “accurately simulates identifiable intervention outcomes”.
- Limited experimental scope: All results come from one synthetic environment with a single nine-variable DAG and a single query and without multiple random seeds.
Questions for authors
see weakness