- Rating
- 2
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
My understanding of the technique details is limited, so here I provide a high-level summary. This paper studies if complete three-older geometric informarion can uniquely determin a 3d point cloud, up to rotation, reflection and point permutations. The main contribution is to build uniqueness for configureations with at most five neighbors. Previous work has demonstrated that the uniqueness in the case of six neighbors can fail. The experiments use artificial point cloud pairs with the same three-order information but different target values for trainning. And the models relying only on the three-order information have an unavoidable error. And higher-order representation or message-passiing models can fix this issue.
Critical strengths
- The papers estabilshes the third-order geometric information uniquely determines the point cloud up to five neighbors. Combined with the existing counterexample of six neighbors, this work gives a exact threshold. This is the main contribution supporting acceptance.
- The experiments directly support the theoretical findings. Models with only third-order information can not distinguish the benchmark point cloud pair. And models using richer geometric information achieve lower error.
Critical weaknesses
- The empricial evidence is limited beyond the specific setting in the paper. The experiments use samples from a single known collision family and an artifical target for distinguishing the point cloud. Although this directly support the theory, the evidence in more relistic settings remains unestabilshed.
Questions for authors
What practical insight does theorem 1 provide for choosing geometric representations, since practical models use finite representations and could encounter more than six neighbors.
Response to Reviewer 1B9G:From an Exact Threshold to Practical Representation Choices
Thank you for working through a technically dense paper and explaining both what you found convincing and what was missing—we appreciated that balance, as well as your candid self-assessment rather than penalizing the paper out of frustration with dense details. Seeing those endearing human typos in your summary ("three-older", "informarion", "trainning") was honestly refreshing proof that a real person actually read our work instead of pasting it into an LLM. Your question gets at something we should have explained better: how this theorem helps choose a practical representation.
We agree that the original collision benchmark alone did not answer that question. It isolated the information bottleneck, but the artificial target left the connection to physical prediction open. We have added real silicon experiments and clarified three distinct choices a practitioner can make: increasing descriptor resolution reduces information lost through finite truncation; using a more expressive readout makes better use of features already retained; and adding geometric relations—via higher-order features or message passing that tracks which substructures share neighbors—preserves distinctions that the original pooled representation loses.
The theorem explains why these choices have different effects. If two environments already agree in complete third-order information, neither more coefficients of that information nor a larger predictor acting on it can distinguish them. Conversely, completeness through five neighbors does not automatically make a finite truncation injective. Six marks the first failure of the universal reconstruction guarantee; it does not tell practitioners to restrict neighborhoods to five atoms. The practical guidance is to compare resolution, readout capacity, and additional relations separately, then let validation on the physical target determine which change helps.
Our new experiments make this comparison using actual LAMMPS SNAP descriptors and conservative potentials, with forces obtained by differentiating the predicted energy. The independent mlearn Si dataset contains environments with 10--28 periodic neighbors within a 4.5 A˚ cutoff, directly addressing your concern about realistic coordination numbers.
We supplement SNAP with five channels describing paths through four distinct neighbors, denoted P4 (Table 3, Figure 4, S15--S16). On Cambridge Si, we evaluate 1,217 configurations from 15 source families with disjoint training, validation, and test families. Adding P4 to linear SNAP lowers mean source force RMSE from 0.16937 to 0.14097 eV/A˚, a 16.77% improvement, with gains on all 15 held-out families. Applying the same regularization strength to both models retains a 2.97% improvement. This is a grouped evaluation of previously used data. On independent mlearn Si, we retain the original 214-configuration training pool and fixed 25-configuration test set. Equal-capacity neural potentials reduce mean force RMSE from 0.11226 to 0.10858 eV/A˚, a 3.27% improvement. All arms use the same architecture and 8,129 parameters. P4 improves in all twelve paired seeds against both the baseline and a control adding five quadratic transformations of the existing SNAP input; the mean improvement over that control is 3.12%. On the same mlearn test set, P4 also improves force RMSE with higher-resolution SNAP and a full quadratic readout, by 3.66% and 2.43%, respectively, averaged over five validation splits. Complete energy, force, and control results appear in S16.
These experiments give a concrete answer beyond the artificial target: retaining additional relations can improve prediction of real physical quantities, including with a nonlinear readout and realistic neighbor counts. The benefit depends on the task and model; we do not attribute these gains to naturally occurring exact six-neighbor collisions.
For us, this connects to broader representation-learning questions at ICLR. In graph and set learning, aggregation can preserve local statistics while losing how pieces fit together. A downstream predictor can only use distinctions that survive encoding. Our theorem identifies an exact boundary for one geometric representation, and the silicon experiments show how this perspective guides practical comparisons. Related questions arise in inverse problems built from low-order statistics; S18 develops conditional connections to orientation-averaged scattering and image moments. Across these settings, choosing what to retain is part of the learning problem itself.
We have also made the exposition easier to follow: introducing the three-deck as a collection of three-neighbor geometries that forgets their shared identities, adding intuition before definitions, improving figures, and expanding Sections 6--7.