- Rating
- 1
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
WorldTraces scores candidate training examples by applying one norm-clipped gradient-ascent step on their training loss and measuring the resulting changes on reference queries. For V-JEPA 2, it keeps the target encoder fixed and measures future-latent prediction, consistency between transformed views, and changes in temporal latent transitions.
Weakness 2 is one of the main reasons for a lower score, I would increase the score if I misunderstood something there.
Critical strengths
-
The problem is useful and well motivated. Separating prediction, representation consistency, and temporal structure gives more specific attribution targets and is desirable.
-
The grouped-intervention results show a consistent ordering across prediction, representation consistency, and temporal structure.
-
The IRIS results provide useful evidence that the method applies beyond JEPA.
-
The sensitivity analysis is thorough, covering the reference queries, target-encoder coupling, and intervention parameter subspace.
Critical weaknesses
-
Figures 3, 6, and 8 evaluate grouped versions of the same gradient-ascent intervention used to compute WorldTraces. This shows that individual scores predict grouped intervention effects, but we need to see whether they predict the effects of changing the training data. Figure 6 also uses this intervention rather than the subset-retraining target used in standard LDS [1].
-
It is unclear whether all V-JEPA 2 candidates were used in the checkpoint’s pretraining. Section 4 includes WebVid in Mini-VM22M, but V-JEPA 2 I believe was trained on YT-Temporal-1B [2]. How was Mini-VM22M constructed, and how did you know if the videos were in pre-training if you did not use the same dataset?
-
Minor: I think you should cite Influence-SSL [3], it also uses consistency between augmented representations to define self-influence in self-supervised models almost exactly as your equation 4.
4: Minor: The main V-JEPA 2 settings are not given. Appendix B.2 does not give the intervention step size, clipping threshold, or predictive prefix-suffix split.
- Grad-Sim and LESS use the JEPA training loss, while WorldTraces directly measures the behaviors used for evaluation. Comparing against a first-order approximation of the same behavioral responses, with the same rank aggregation, would help establish whether the gains come from the checkpoint intervention or simply from choosing different attribution targets.
[1] Park, Sung Min, et al. "Trak: Attributing model behavior at scale." arXiv preprint arXiv:2303.14186 (2023).
[2] Assran, Mido, et al. "V-jepa 2: Self-supervised video models enable understanding, prediction and planning." arXiv preprint arXiv:2506.09985 (2025).
[3] Harilal, Nidhin, et al. "Where Did Your Model Learn That? Label-free Influence for Self-supervised Learning." arXiv preprint arXiv:2412.17170 (2024).
Questions for authors
-
Are the subset gradients in Figure 3 averaged as in Eq. (2), and is the intervention step size fixed across subset sizes? Because the Random effects grow approximately with subset size.
-
How is Top–Bottom separation computed in Figure 4? The equal-weight result does not appear to match the difference between the corresponding Top and Bottom percentages in Figure 3.
-
How are the optimizer states needed for LESS’s Adam-aware candidate updates obtained [4]? Does the IRIS implementation use Adam-adjusted updates or projected raw gradients?
-
What are the total runtime and peak GPU memory for WorldTraces, Grad-Sim, and LESS under the candidate and query settings used in Figure 6?
[4] Xia, Mengzhou, et al. "Less: Selecting influential data for targeted instruction tuning." arXiv preprint arXiv:2402.04333 (2024).