[W1] The contribution cannot be identified. The authors themselves acknowledge that shared gates were already used by CoIBA and deterministic gating by NIB (Sec. 2), and the information-bottleneck motivation in the title is invalidated by the authors in Appendix A. The remaining contribution is the combination of "CE endpoint optimization + unsigned path integration", yet there is no experiment comparing the central design choice, the unsigned score si, against signed IG or the endpoint-weighted score α^isi. The authors state in Sec. 3.3 and Appendix F that this comparison "remains necessary". The paper thus defers the justification of its own contribution to future work.
[W2] The methodology does not define a single method. Instead of describing a design, Sec. 3 reports the result of statically reading a "recovered server source". The objective is never fixed: the paper does not commit to Llogit or Lprob and writes "We use L for the scalar loss actually chosen", while Sec. 4.1 proves that the two gradients are generally different vectors. Two integration rules coexist, the "intended" full-interval right-endpoint rule and the "recovered" truncated trapezoidal rule over [1/m,1]. Algorithm 1 is titled "recovered numerical ordering". A reviewer cannot determine which method is being proposed, and the referenced source cannot be inspected.
[W3] The main results are irreproducible, and the authors admit this. Statements such as "The original archive contains no main-result implementation", "No experiment was rerun", and "code-to-result bindings remain unresolved" recur throughout the text. The submitted tbk.py only generates attribution maps, hardcodes opt_steps=20 which differs from the Table 2 setting (T=50 for ViT, T=30 for DeiT), contains no evaluation code or baseline implementations, lacks the input tensors img_batch.pt and label_batch.pt, and generate_attributions.py references an undeclared args.dataset so that execution fails immediately with an AttributeError. The README merely states that this was "preserved". Moreover, the follow-up setting described in Sec. 5.2 (batch size 8, batch-mean CE) does not match the submitted code (batch size 1), suggesting that the source referenced in the paper and the submitted source are yet another pair of different versions.
[W4] The empirical evidence is very weak. The main table reports no standard deviations and no image count. In the paired bootstrap (Table 3), Insertion is the only metric whose confidence interval excludes zero, and according to Table 4 the raw-map Insertion is 0.576, only 0.0056 above CoIBA (0.571), with no confidence interval provided for this raw difference. The only significant result therefore arises from the 3×3 mean-smoothing post-processing. Furthermore, Table 5 shows that the all-open gate with no optimization at all (ROAD 0.272, Insertion 0.582) is only marginally behind the learned gate (0.285, 0.594), casting doubt on whether Stage A is needed. LeGrad, TIS, MDA, TokenTM, and LibraGrad, all cited in related work, are absent from the numerical comparison.
[W5] The theoretical results do not support the method. Lemma 1 and Theorem 1 are at the level of the chain rule and the triangle inequality, and the authors' own counterexamples (L=C+α1−α2 with ΔL=0 but s1+s2=2, and L=C+εsin(kα) with arbitrarily large unsigned mass) show that the unsigned score can grow independently of the loss change. The bound holds "for any qualifying endpoint, including random ones", so it says nothing about TBK's particular endpoint. Notation is also unclear: the shape of h(ℓ) is not specified, and it is used as a matrix in Eq. (1) but as a per-token vector hi(ℓ) in Eq. (5).
[W6] Readability and maturity. The paper is very difficult to read. The methodology section is filled with code archaeology and the experiments section with disclaimers about evidence of uncertain provenance, so that a reader struggles to the end to determine what the proposed method is and what has been shown. The repeated vocabulary of "existing", "retained", "recovered", "unverified", and "unresolved" conveys that the authors are not in control of their own implementation and results. The manuscript reads as a revision in which overstated claims from a previous version were retracted, leaving essentially nothing behind. The candor about limitations is acknowledged, but candor does not substitute for a contribution. Overall this is a highly immature manuscript that does not reach the standard of a conference submission. It should be resubmitted only after providing a single definitive method specification, a reproducible implementation, and controlled experiments on the core design choices.
For these critical reasons, I regret that my recommendation is to reject.