There was a robust discussion on the merits and novelty of this work after the rebuttal from the authors. There was some confusion as to whether this work is truly the first to-be-published work that introduces BrainScore. We concluded that given the pre-print only versions of the work thus far, this qualifies as a genuinely new contribution (wrt. With that in mind: the authors would do well do describe the details of the BrainScore in more detail in the camera ready version. Otherwise, everyone is excited about the novel aspects (architecture, experiments, metric etc) of this work so I wholeheartedly recommend this work to be accepted at NeurIPS.

Three knowledgeable referees support acceptance for the contributions, notably for a proposed approach to extend CNNs with generative feedback, while one reviewer supports (marginal) reject. This paper was extensively discussed post-rebuttal -- especially in light of the fact that the initial evaluation on brainscore appeared to have been flawed and that the results on brainscore have not just changed quantitatively but also qualitatively. I also agree with R4 that the overall evaluation is not particularly compelling as a general model of object recognition (see R4 points) as opposed to maybe a narrower approach to build robustness to adversarial attacks. Overall, there appears to be sufficient support because of the novelty of the idea to accept this paper but all reviewers agreed that the quantitative evaluation on brainscore needs to be fixed and claims revised accordingly.

With the rise of Large Language Models (LLMs), the novel metric "Brainscore" emerged as a means to evaluate the functional similarity between LLMs and human brain/neural systems. Our efforts were dedicated to mining the meaning of the novel score by constructing topological features derived from both human fMRI data involving 190 subjects, and 39 LLMs plus their untrained counterparts. Subsequently, we trained 36 Linear Regression Models and conducted thorough statistical analyses to discern reliable and valid features from our constructed ones. Our findings reveal distinctive feature combinations conducive to interpreting existing brainscores across various brain regions of interest (ROIs) and hemispheres, thereby significantly contributing to advancing interpretable machine learning (iML) studies. The study is enriched by our further discussions and analyses concerning existing brainscores. To our knowledge, this study represents the first attempt to comprehend the novel metric brainscore within this interdisciplinary domain.