- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposed a neural-guided symbolic search method. The method uses symmetry-typed expression graphs to enforce prescribed ODE symmetries and sub-expression semantics to guide search. The author claims that their design supports free-form, non-polynomial dynamics, and can be further integrates into a neural-guided Monte Carlo Tree Search.
Critical strengths
- The problem is clear and well motivated, the gap between fixed invariant libraries and unconstrained symbolic search is interesting.
- The design is direct: aonstraints are built into representation.
- The reported results are comprehensive.
Critical weaknesses
- In my opinion, the method is a combination of symmetry-typed expression-graph construction with path-conditioned functional targets for sub-expressions, integrating both into neural-guided MCTS for ODE discovery. The individual ingredients have clear precedents.
- Equation (8) defines a child target by applying the inverse of its parent operator. But the mask in Equation (8) is set using only whether the parent target and sibling semantics are available. The target-availability mask seems not check whether an operator can actually be inverted.
- The ODEBench comparison does not isolate the semantic components: I suppose that section 4.4 attributes S2GSR’s gains over GSR to sub-expression semantics and path-conditioned guidance. But that is a comparison of the full methods.
- The reported recovery rates lack uncertainty and an operational definition.
- Given the Figure 2, “significantly outperforms library-based SINDy methods” is too strong and not sufficiently verified.
Questions for authors
- What are the core innovations of S2GSR? In what specific ways does the combination of "symmetry-aware graphs," "sub-expression guidance," and "Monte Carlo Tree Search" (MCTS) surpass existing methods?
- In Equation (8), how is it ensured that the parent operator is invertible, thereby allowing for the derivation of a child target?
- Could ablation studies be added for the ODEBench experiments to clarify which specific components of S2GSR contribute to these performance improvements?
- How is it determined whether a method has successfully recovered the complete ground-truth equation? Are algebraically equivalent expressions considered correct?
- Figure 2 indicates that S2GSR performs "significantly better" than library-based methods like SINDy. What statistical evidence supports this conclusion? Does "significantly" here imply statistical significance, or does it simply mean that S2GSR achieved higher scores in the experiments?
5 comments
Responses to Reviewer n9HH [2/2]
R3. ODEBench ablation
[W3, Q3] “The ODEBench comparison does not isolate the semantic components” and “Could ablation studies be added for the ODEBench experiments [...]?”
We agree that the comparison with GSR is a comparison of full semantic features. We added an ODEBench ablation with an identical backbone, which isolates the semantic components. Under trivial symmetry, we compare structural guidance only (None), sub-expression semantics (Sem-only), and the full model (Sem+Align), keeping the graph transformer, canonicalization, constant optimization, and search budget fixed, on all 63 systems with noise (percentage of systems with ):
| Variant | ||
|---|---|---|
| None | [50.79%] | [55.56%] |
| Sem-only | [55.56%] | [63.49%] |
| Sem+Align (full) | [58.73%] | [65.08%] |
Each semantic component raises the success rate in both settings (None → Sem-only → Sem+Align: 50.79% → 55.56% → 58.73% at , and 55.56% → 63.49% → 65.08% at ), while the structure-only variant is on par with GSR (52.38% and 55.56%), so the gains over GSR come from the semantic components rather than the backbone.
Revision: we added this ablation table to Appendix E.5 (Table 10), and Sec. 4.4 now attributes the gains over GSR only as supported by it.
R4. Definition and uncertainty of the recovery rate
[W4, Q4] “The reported recovery rates lack uncertainty and an operational definition.” and “Are algebraically equivalent expressions considered correct?”
We thank the reviewer for this comment. Both were given in Appendix E.1 and Table 9. Following the EquivSINDy evaluation (Yang et al., 2024), a seed counts as recovered only if, after algebraic simplification, the inferred and ground-truth fields contain exactly the same symbolic terms in every component, regardless of coefficient values; algebraically equivalent expressions are therefore counted as correct. Table 9 reports Wilson 95% intervals over the 100 seeds for the recovery rate (RR).
R5. Use of “significantly” in Sec. 4.4
[W5, Q5] “‘significantly outperforms library-based SINDy methods’ is too strong” and “Does ‘significantly’ here imply statistical significance [...]?”
We thank the reviewer for this comment. We meant a large margin (18-62 percentage points higher) rather than statistical significance, and we have removed the word.
We thank the reviewer again for the time and constructive comments, which helped us improve the precision of our definitions and claims. We hope our responses address your concerns, and we look forward to your feedback.
Best regards,
The Authors
Follow-up on Responses to Reviewer n9HH
Dear Reviewer n9HH,
Thank you for your careful review. As the discussion period closes today, we wanted to follow up on our response. In brief, we:
- clarified the core innovations of S$^2$GSR relative to GSR, semantic backpropagation, and hnMCTS;
- pointed to the invertibility check of Eq. (8), described in Appendix C.2;
- added an ODEBench ablation with an identical backbone, which isolates the semantic components (Appendix E.5, Table 10);
- pointed to the operational definition of the recovery rate and its Wilson intervals (Appendix E.1, Table 9);
- removed "significantly" from Sec. 4.4.
We would be glad to answer any remaining questions. If our response has addressed your concerns, we would appreciate it if you could consider updating your assessment. We would like to express our sincere appreciation again for your time and effort in reviewing our work.
Best regards,
The Authors
Responses to Reviewer n9HH [1/2]
We thank the reviewer for the careful review and for recognizing the motivation of bridging fixed invariant libraries and unconstrained symbolic search, the direct design that builds constraints into the representation, and the comprehensiveness of our results. We also value the Weaknesses (W) and Questions (Q) raised in the review. Below, we respond to each concern in order; all revisions are marked in blue in the updated PDF.
R1. Core innovations of S$^2$GSR
We thank the reviewer for this question. S$^2$GSR differs from each of these existing methods in important ways and unifies them to address two challenges that matter in ODE discovery: enforcing physical symmetries exactly in a free-form search space, and guiding the search toward hard, non-polynomial dynamics. Specifically:
Together, these improve recovery beyond both library-based and free-form methods: on the non-polynomial systems, S$^2$GSR reaches RR 0.36 and 0.58, compared with at most 0.12 for all the tested baselines, including the symmetry-aware EquivSINDy-c (0.00) and GSR (0.05 and 0.12) (Table 3). Table 4 shows that each component contributes: on NP-SO(2), symmetry typing raises RR from 0.06 to 0.22, and semantic guidance further raises it to 0.36.
R2. Invertibility in Eq. (8)
We thank the reviewer for the interest in this point. Invertibility is checked in our implementation, which has been discussed in Appendix C.2, where the manuscript line 257 (line 289 in the revised PDF) referred to it. There, a two-tier dispatch computes the target in closed form only for operators that are invertible at the child node's slot (additive slots, multiplication and division away from zero, and strictly monotone unary operators such as exp, log, and odd powers); for all others (e.g., even powers, ∥⋅∥2, sin, and cos), the target is masked for the whole subtree below the operator, which then uses the signature-indexed embedding.