- Rating
- 3
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper introduces Attribution Vergence, a measure of the change in Rényi-2 effective dimensionality of internal attributions before and after feature aggregation. The authors provide mathematical properties of the measure and evaluate its correlations with grokking progress and adversarial transferability.
Critical strengths
- The paper studies an interesting problem: whether internal attribution organization can provide useful indicators of model behavior across different architectures and tasks.
- The paper looks well-written and polished.
Critical weaknesses
I didn't identify any critical weaknesses.
Questions for authors
None
2 comments
Dear Reviewer,
Thank you again for your positive assessment. Please let us know if you have any further questions or would like clarification on any aspect of the paper.
Our revision of the manuscript is marked in blue. The main updates are:
- Clarified the research context and significance of a common observable (Section 1).
- Added comparisons with Fourier-Gini progress measures (Section 4.2, Table 2).
- Added Fourier-based circuit associations and routing interventions to investigate task-dependent attribution organization (Section 4.2, Appendices E.3–E.4).
- Added robustness analyses across attribution references, objectives, and paths (Figure 5 in Section 4.2, Appendix G.2).
- Clarified the meaning and theoretical grounding of “local complexity” (Sections 2–3).
Response to Reviewer
We thank the reviewer for the positive assessment and for recognizing the strengths of our theoretical framework and empirical evaluation. In the revised manuscript, we further clarify the connections to related work, add theoretical analysis and experiments on the Fourier-circuit structure, and evaluate the sensitivity to attribution choices. Our Overall Comments also explain the broader scientific motivation and contribution of the measurement framework. We hope these additions and clarifications provide a clearer understanding of the work.