- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The authors present a method to use equation-derived priors to structurally embed approximate or exact ground truth equation priors into neural operator architectures to improve performance. The authors showcase their results of learning a physics residual using FNO and DeepONet and their results on learning with structurally-embedded equation priors using DeepONet. The results demonstrate improvements over baselines.
Critical strengths
The experiments are thorough and applied to a wide range of systems and benchmarks. I appreciate error comparisons against training budgets (Figure 2) and the diverse set of problems (e.g., Figure 3) that the authors compared against.
Critical weaknesses
The main weakness of this paper is its scope. Please correct me if I misunderstood, but the non-DeepONet experiments appear to be only learning a residual against a given prior using an FNO, which I would argue is a good baseline but perhaps not particularly novel as a proposed method. On the other hand, injecting structural priors in the architecture is a novel and interesting area, but the experiments appear to me to be primarily useful only for DeepONet architectures. Again, please correct me if I misunderstood here.
If my understanding is correct, I would concretely recommend that the authors present more general recipes for incorporating equation priors into neural operator architectures and perhaps explore different types of architectures, such as attention-based architectures or ones using different bases (non-Fourier). This would strengthen the paper substantially.
Also, physics-informed or “physics-embedded” methods are largely useful up to their concrete applications. If computational resources and time permit, I would recommend that the authors expand their experimental set beyond simple toy settings and explore larger real-world problems (e.g., weather forecasting, where there is a substantial amount of dataset and training frameworks, comes to mind, although I understand that this may be outside the scope of a methods paper).
Furthermore, in my personal opinion, the merits of this paper are overshadowed by lack of clarity in the writing, and much of the text reads as though it may have been AI-generated. While I cannot verify that LLMs generated the text, I do believe that the style seems close to that of frontier language models. Below I have some selected examples of what I am referring to:
Instances of terminology that should be changed or clarified:
- “Learner” in paragraph 4
- “Instance-side factor” (line 140)
A few sentences where AI-like phrasing may obscure understanding or sound unprofessional:
- “For a direct prior this residual is not an arbitrary leftover.” (line 150)
- “leaving all four at their data-driven defaults gives a raw operator” — what is a “raw operator”?
- “Two qualifications.” - line 357
- Figure 3 caption: “What the rank-two prior removes.”
- “The gains are conditional.” (Line 463)
I understand that some of these may be stylistic choices, and I do not intend to penalize the authors for these choices, although I do personally recommend that they change some wordings to maintain an academic tone. My main concern is when stylistic writing choices begin to conflict with reader understanding, which is particularly important in Sections 2 and 3.
Minor notes:
- Introduction: “and even where it is exact, a lower residual loss does not guarantee a more accurate solution.” Can you expand on this in the text? A reader may ask how the result could be inaccurate if the ground truth equation is satisfied.
- It would be useful to include some examples of where “direct” and “indirect” priors could be derived from in section 2.
Questions for authors
- Does the structural injection only apply to DeepONet? It seems like it relies on the trunk/branch structure and is not architecture-agnostic.
- What are the specific instance/spatial factors and structural injection basis functions that you use for your experiments? It is possible I missed them in the main text, but I believe these should be mentioned clearly in Section 3, at least for 1-2 prototypical systems.
8 comments
Response to Reviewer VYxh (1/2)
Main weakness
Reviewer’s comment: Main weakness. The non-DeepONet experiments only learn a residual with an FNO, which is a good baseline but not novel, and structural injection appears useful only for DeepONet.
Response.
The reviewer reads both points correctly for the submitted version, and we address the second with new experiments.
Residual learning with FNO. We agree that learning a residual on top of a prior is not new as a method, and we do not propose it as one. In the paper it is Level 2, one of three ways of exposing the same equation that we compare: as a loss, as a prior, and as a basis. The contribution is the comparison and what it shows. Used as a loss, the equation helps little, and its bias toward the approximate equation does not shrink with more data (our response to Reviewer ycrY, W2–Q2, shows this pull directly). Used as a prior, it helps in proportion to how much of the solution it already resolves, and a strong backbone such as FNO can close the gap. Used as a basis, it gives the largest and most robust gains, and where the basis carries structure the backbone does not have, these survive a change of backbone. The FNO experiments are therefore there to test the first two uses under a strong backbone, not to propose residual learning.
Structural injection beyond DeepONet. This was a fair limitation, and we address it with new experiments that we will add to the paper: the general comment on attention-based backbones applies the injection to GNOT and Transolver on all six benchmarks with an equation-derived basis (Tables R1–R2 and R3).
Presentation. We take the low presentation score seriously. In the revised PDF, the three uses of are placed side by side in Fig. 1 and Table 1 with one notation throughout, a new table in Sec. 3 lists the factors of every benchmark together with the Pipe and annulus examples, and the per-benchmark constructions stay in the appendix, so that the main text follows a single line: where the equation enters, and what each choice buys.
Q1, Q2
Reviewer’s comment: Q1. Does structural injection apply only to DeepONet, given its reliance on the trunk/branch structure? Q2. Which instance and spatial factors and basis functions are used, at least for one or two prototypical systems?
Response to Q1.
No; see the general comment on attention-based backbones and the response to the main weakness above.
Response to Q2.
We agree that these belong in Sec. 3 and will move them there. Each basis column factorizes as : a spatial factor that depends on the geometry , and a source factor that depends on the remaining inputs . Two examples:
-
Pipe flow. is Stokes flow in the channel. The spatial factors are the responses of the discretized Stokes operator of each shape to smooth sine sources , , , with the mesh coordinates along and across the channel, placed in the interior rows of the vorticity equation; the -th column is the horizontal velocity of that response, scaled by its RMS in a straight channel (). There is no source factor (), and the coefficients are learned from the nine shape coordinates. All columns share the matrix of the prior solve, so they cost one factorization per shape.
-
Annulus. The unit disk is split by four interface radii into a central disk and four concentric rings. The prior imposes continuity of the field and its flux at the interfaces; the reference adds an interface thermal resistance. The source factors are the Fourier coefficients of the boundary data on , with polar coordinates, , . The spatial factors are separable, , with and, in each region, the two radial solutions and (only the first in the central disk; are the interface radii, , ), nine radial functions in all (). The coefficients are learned from the four interface radii.
We will add a table to Sec. 3 that lists , and for every benchmark, following the forms already given in App. B.8.
Recommendations
Reviewer’s comment: Recommendations. Give more general recipes for injecting equation priors into other architectures (attention-based, non-Fourier bases), and extend the experiments to larger real-world problems.
Response to Reviewer VYxh (2/2)
(continued: Recommendations)
Response.
A general recipe and other architectures. We followed this recommendation; the recipe and the attention-based results are in the general comment. On non-Fourier bases: none of the three backbones uses one (DeepONet learns its trunk, GNOT attends over input tokens, Transolver learns a soft partition into slices), and the fixed bases are Green responses, Laurent series or transfer-matrix modes, depending on the equation.
Larger real-world problems. We agree that our benchmarks are small, though several use realistic geometry (pipe flow, airfoils, a plate with a hole). Weather forecasting is autoregressive, where an approximate model enters as a solver-in-the-loop correction (response to ycrY, W6-P1). We will name large-scale and time-dependent problems as the main future direction in Sec. 5.
Writing and minor notes
Reviewer’s comment: Writing. Several terms and phrases read as AI-generated and obscure Sections 2–3; the minor notes ask why a lower residual need not mean a more accurate solution, and for examples of direct and indirect priors.
Response.
We thank the reviewer for the specific examples. As stated in our AI-use disclosure, English is not our first language, and we used language models to draft and translate parts of the text. We checked every passage ourselves and judged it accurate and academically appropriate, but the reviewer’s examples show that this judgment was not sufficient: some phrasing that read naturally to us obscures the meaning for a reader. They point to real problems of clarity, and we will rewrite Sections 2 and 3 in a plainer academic register, defining each term when it first appears. For the cases listed:
| Current text | Revision |
|---|---|
| “Learner” | “the neural operator” in the introduction; “the corrector” where it refers to (App. H, K) |
| “Instance-side factor” | “the input-dependent factor produced by the branch” (for the indirect prior, the per-instance numbers fixed by the equation) |
| “raw operator” | “the backbone trained on data alone, without equation information (RAW)” |
| “For a direct prior this residual is not an arbitrary leftover.” | “When is linear and invertible and , share boundary conditions, the residual is fixed by the terms that omits, through the inverse of its operator (Lemma 1).” |
| “Two qualifications.” | Removed in both places (Sec. 4.2, App. C.6); the caveats are stated in full sentences. |
| “What the rank-two prior removes.” | “Reference pressure (top), rank-two prior (middle) and residual (bottom) on three held-out cases; shared color scale.” |
| “The gains are conditional.” (Sec. 5) | “The gains depend on how much of the solution the prior resolves, on the backbone, on whether the basis spans the residual, and on the data available to estimate its coefficients (Secs. 4.1–4.3).” |
Minor note 1. We will expand the sentence, with the reference already cited there (Chen et al., 2026, arXiv:2606.06164). A residual loss is evaluated at a finite set of points, and the loss can admit fields that are not solutions but have a lower residual than the true solution. Chen et al. give a direct example with the exact equation: on their ice-melting benchmark, one optimizer drives the residual sixteen times below another yet ends with a higher error, because a diffused interface has smaller gradients, and hence a smaller residual, than a sharp interface; the trained model’s residual is even two orders of magnitude below that of the reference solution (their App. I). For time-dependent problems, a small residual averaged over the time domain can also hide a solution that violates causality (their Sec. 3). We will keep this separate from the misspecification bias of an approximate (Proposition 1), which is what our 3D layered results illustrate.
Minor note 2. We will add examples at the start of Sec. 2. Direct priors (17 of our 18 benchmarks) return the field from without labels, either by a numerical solve (the reaction, heat and battery benchmarks, and a Stokes solve standing in for Navier–Stokes on Pipe) or by a classical analytic construction (a spectral expansion, a transfer matrix for layered media, an effective-medium coefficient for heterogeneous media, or a complex potential in plane elasticity). The indirect prior (AirfRANS) returns only the per-instance factor from the momentum equation; its spatial profile is fitted by least squares on the same training labels.
Summary of our response to Reviewer VYxh
We thank the reviewer for the careful reading. The reviewer's reading was accurate for the submitted version; we address the main limitation with new experiments.