- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper investigates how graph structure affects the memory resources required for latent multi-hop recall and the composability of modular memories. It introduces measures of support usage, macro-decomposition credit, and realizable width, and derives a constructive capacity upper bound, a restricted entry-count lower bound, and a conditional composition failure bound. Controlled experiments on gated-memory architectures examine support-dependent capacity scaling, show that compression savings depend on allocation, and suggest that trained macro gains primarily reflect shorter retrieval depth rather than cross-query reuse. Additional oracle controls isolate the effect of cross-module representation alignment. The empirical findings primarily concern these controlled substrates; pretrained-model experiments remain capacity-threshold censored.
Critical strengths
- A concrete structural account of memory cost. The paper distinguishes support usage, macro decomposition, and realizable width, providing an explicit construction that captures differences obscured by raw fact counts. Its separation of memory parameters from dictionary and parsing resources makes the resulting guarantees more interpretable. This offers a useful foundation for studying how graph structure affects the cost of storing and executing multi-hop knowledge.
- Informative controls separating compression from implementation and learning effects. The allocation and private-macro controls show that fewer discrete associations do not necessarily translate into fewer implemented parameters or explain trained gains. The receiving-complete frame controls also separate representation mismatch from missing support. These comparisons provide useful mechanism-level information beyond reporting whether a particular memory system succeeds.
Critical weaknesses
- The scientific increment beyond the assumptions is insufficiently established. Theorem 2 requires witness execution and limits each entry to one labeled macro-fact per slot, imposing much of the underlying counting structure. Theorem 3 relies on receiving-cap overlap and path separation, which perform substantial explanatory work in connecting interface incompatibility to failure. These restrictions do not invalidate the results, but the paper needs to establish more clearly what non-obvious understanding remains beyond them and how it advances the closest capacity and associative-memory results. Section 2 provides insufficient comparative analysis, while the dense exposition lacks a worked graph-to-memory example connecting the definitions, guarantees, and experiments. Consequently, the paper’s central conceptual contribution remains difficult to assess.
- The quantitative and mechanistic interpretations require stronger evidential support. Appendix D states that the threshold-bracket audit fixes rung-level pass/fail verdicts without re-estimating uncertainty from the underlying learning-rate runs. The sensitivity of the reported scaling slopes and support-predictor comparisons to these decisions therefore remains unclear. Likewise, the private/shared-macro controls establish no detectable reuse advantage at the tested resolution, but do not by themselves uniquely identify reduced retrieval depth as the explanation for trained gains. The paper acknowledges several measurement limitations; however, their consequences for these quantitative and mechanistic interpretations need to be carried through more explicitly. These are fixable concerns about inference, rather than allegations that the reported measurements are incorrect.
Questions for authors
- Conceptual contribution: After accounting for the witness-execution, entry-representation, and composition assumptions, what are the principal non-obvious conclusions relative to the closest capacity and associative-memory results? Please identify which explanatory steps are established by the analysis rather than supplied by the assumptions.
- Threshold robustness: Using the existing runs, how stable are the reported scaling slopes and support-predictor rankings to threshold-bracket resolution and learning-rate/seed-level pass/fail variation? This would help assess the uncertainty omitted by treating the archived rung-level verdicts as fixed.
- Mechanism attribution: Which aspects of the existing macro controls distinguish reduced live retrieval depth from other changes introduced by macro encoding? In particular, what supports the retrieval-depth attribution beyond the absence of a detectable private/shared threshold difference?
We thank the reviewer for identifying the need to distinguish assumptions from deductions, quantify threshold uncertainty, and avoid overattributing the trained macro effect. The revised manuscript now separates these claims explicitly.
Critical weakness 1 / Question 1 — theoretical increment
Response. We agree these are substantive assumptions, not empirical findings. Theorem 2 assumes witness-executing, slot-factorized resolution, but derives the number of distinct entries that must survive on a sufficiently large correctly answered query set. Pair-balancedness bounds the support deleted by omitted query mass; selector optimality is required only to identify the reference-selector H−S; explicit entries are required to convert entry counts into scalar parameters. A direct answer shortcut or superposed representation may lie outside this lower bound.
Theorem 3 assumes receiving-cap overlap, a frame-nonaligning latent interface, and path-separating execution. Its derived step converts a local crossing incompatibility into a workload-level confabulation-plus-abstention floor:
E[errconf+abst]≥(1−pch(d)−δalign)crosskuniq.It is a conditional mechanism theorem, not a universal impossibility result. We have clarified both theorem scopes and the increments relative to Ravfogel et al. (2026): retained fact–slot support, admissible witness compression, and realizable-width-aware construction. The revised worked example makes the full resource accounting explicit.
Critical weakness 2 / Question 2 — threshold robustness
Response. The archived thresholds are intervals L<P∗≤U, with median bracket width about 2.1×. E-T reanalyzes the 11 non-control families using 20,000 independent per-family draws uniform in logP∗ within these brackets. The slope median is 0.946, the central 95% bracket-sensitivity interval is [0.795,1.098], and the sampled range is [0.688,1.196]. This is not a seed-level confidence interval or 20,000 independent training replications. It supports a roughly linear trend within the tested gated substrate under that sensitivity model, not a uniquely identified law.
The predictor ranking is unstable: H0 wins just 18.3% of realizations. Raw ∣E∣ and H2 never win among the tested predictors under this procedure. We therefore removed the unique-best-predictor claim. The later restricted-adapter Transformer experiment (E-S) also fails to reproduce an H ordering across structural families, with additional optimization sensitivity; this is reported rather than presented as confirmation.
Question 3 — macro mechanism attribution
Response. Shared and query-private macro arms keep segmentation and active execution depth matched while removing cross-query identity reuse in the private arm. Thresholds agree exactly in 27/30 family–seed–budget cells and within one rung in 29/30. In
reuse_hi3, the private arm can store more associations than the free arm yet require fewer table parameters. Thus cross-query reuse is not necessary for the observed trained gain at the tested resolution. Because macro encoding and optimization also change, we now say the result is consistent with fewer live lookups, not that it uniquely proves retrieval-depth causation.We hope the narrower claims and explicit sensitivity and negative findings address your concerns. We respectfully ask you to reconsider your score in light of these revisions.