- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper examines why small Hamiltonian errors can produce inaccurate orbital energies and wavefunctions. In the reference orbital basis, the authors separate energy shifts, occupied–virtual mixing, and rotations within occupied or virtual subspaces. They introduce a Gaussian-smoothed cumulative LDOS loss to capture both spectral positions and spatial orbital densities. Fine-tuning QHNet, SPHNet, and WANet on four QH9 splits improves downstream predictions without changing the architectures. On stable-id, HOMO–LUMO gap MAE decreases by 49–79% relative to the pretrained models and 37–65% relative to the tested WALoss baseline, with little change in Hamiltonian MAE.
Critical strengths
-
The physical motivation is clear. Density matching misses energy shifts when orbital shapes and occupations remain unchanged, which gives a concrete reason to retain energy resolution. The continuous-representation analysis provides a useful theoretical account under its stated assumptions.
-
The experiments include shared starting checkpoints, matched fine-tuning protocols, and element-wise-only continued-training controls. Density-only, peak-LDOS, and WALoss comparisons help identify the effects of the auxiliary objective.
Critical weaknesses
-
The relationship to existing objectives needs more attention. NextHAM [1] combines real-space and reciprocal-space supervision with separate weights for low-energy, high-energy, and cross-subspace errors. Cignoni et al. [2] jointly optimize eigenvalues obtained by diagonalizing the predicted Hamiltonian and Löwdin atomic charges. Suman et al. [3] extend this approach to additional electronic observables. These studies are relevant to the proposed combination of spectral and spatial supervision. The paper does not adequately explain what cumulative LDOS adds beyond these approaches.
A direct predicted-eigenvalue loss combined with the existing density loss would be an informative comparator. Density-only supervision already captures most of the QHNet stable-id gap improvement: 2081 μHa versus 2027 μHa for cumulative LDOS. The additional gains on SPHNet and WANet are larger, approximately 19% and 28%. This variation deserves more discussion.
-
The supplied evaluation code does not fully match the manuscript. Appendix E defines orbital similarity using the overlap-matrix inner product, . In contrast,
cumldos/metrics.py, line 35, computes the Euclidean cosine similarity of the coefficient vectors. These are different quantities in a nonorthogonal AO basis. The discrepancy leaves the definition of the reported ψ values unclear.The SCF timing protocol is also unclear. In
scripts/scf_init.py, the generalized eigensolve and initial-density construction occur before the SCF timer starts. It is unclear whether this cost is included in the externally suppliedt_inf. Appendix F states that Table 12 includes both the model forward pass and eigensolve, but the supplied script does not make that accounting explicit. -
The theoretical guarantees need to be separated from the properties of the sampled loss. Identifiability is established in continuous real space and over a continuous energy interval; training uses 256 spatial points and 64 energies. Appendix B acknowledges unresolved directions at the actual sampling density. The non-saturating restoring-force result also assumes a single displaced level with fixed orbital shape and is limited by the finite energy window. These conditions belong alongside the main claims.
Proposition B.7 likewise does not establish that the increase in matrix error must be small. The small trade-off observed in the tables should be presented as an empirical result.
-
The empirical scope and uncertainty remain limited. All experiments concern small, closed-shell H/C/N/O/F molecules at the B3LYP/def2-SVP level. The shifted splits do not test new elements, periodic systems, or SOC Hamiltonians. Broader chemical spaces have been studied with DeepH-2 [4], HamGNN [5], and NextHAM [1], while QHNetV2 [6] and QHFlow2 [7] provide more recent molecular predictors. Transfer of the proposed loss to these settings remains untested.
The main comparisons lack repeated-seed uncertainty, which matters for the smaller margins. Training cost is appreciable: Table 13 gives approximately 49% overhead per fine-tuning step. The approximately 5% figure uses pretraining cost as the denominator. Table 12 shows little additional SCF acceleration over the pretrained model, so the practical case rests mainly on improved single-shot properties.
References.
[1] Yin et al. Advancing Universal Deep Learning for Electronic-Structure Hamiltonian Prediction of Materials. ICLR 2026.
[2] Cignoni et al. Electronic Excited States from Physically Constrained Machine Learning. ACS Central Science 10, 637–648 (2024).
[3] Suman et al. Exploring the Design Space of Machine Learning Models for Quantum Chemistry with a Fully Differentiable Framework. JCTC 21, 6505–6516 (2025).
[4] Wang et al. Universal materials model of deep-learning density functional theory Hamiltonian. Science Bulletin 69, 2514–2521 (2024).
[5] Zhong et al. Universal Machine Learning Kohn–Sham Hamiltonian for Materials. Chinese Physics Letters 41, 077103 (2024).
[6] Yu et al. Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Frames. ICML 2026.
[7] Kim et al. Machine Learning Hamiltonians are Accurate Energy-Force Predictors. ICML 2026.
Questions for authors
-
Which definition was used for the reported ψ values: the overlap-matrix inner product in Appendix E or the Euclidean coefficient cosine in the supplied code?
-
Does the total time reported in Table 12 include the generalized eigensolve and initial-density construction? Please clarify what the externally supplied
t_infcontains. -
Please clarify the relationship to the objectives in [1–3] and state the finite-sampling and energy-window conditions alongside the main theoretical claims.
A matched QHNet stable-id comparison with direct eigenvalue matching combined with the existing density loss would help establish the contribution of the cumulative LDOS representation. Any available repeated-run results would also help assess the smaller differences.
4 comments
Response to Reviewer EXdn - Part 2/3
W1: "A direct predicted-eigenvalue loss combined with the existing density loss would be an informative comparator. Density-only supervision already captures most of the QHNet stable-id gap improvement [...]. This variation deserves more discussion."
We ran it on QHNet, SPHNet and WANet (stable-id, same protocol, weights matched by gradient share) and show it next to the rows of Table 1 (Table 15 in the new Appendix G.8 has all eight metrics). Each term is added to the element-wise loss. All entries are mean absolute errors in Ha except (%). Rows marked 3 seeds are means over three seeds, and the others are single runs. Bold marks the best downstream value in each block, and the matrix error H is not bolded.
| QH9 stable-id | H | HOMO | LUMO | gap | ||
|---|---|---|---|---|---|---|
| QHNet | ||||||
| pretrained | 77.56 | 1041 | 9445 | 9632 | 1206 | 96.28 |
| + WALoss (3 seeds) | 78.06 | 875 | 6124 | 6448 | 671 | 96.61 |
| + density | 76.82 | 719 | 1575 | 2081 | 356 | 97.87 |
| + eigenvalue + density | 76.35 | 671 | 1285 | 1813 | 353 | 97.96 |
| + cumulative LDOS (ours, 3 seeds) | 74.87 | 647 | 1354 | 1868 | 336 | 97.98 |
| SPHNet | ||||||
| pretrained | 36.60 | 345 | 1309 | 1554 | 380 | 99.06 |
| + WALoss (3 seeds) | 37.32 | 344 | 929 | 1235 | 285 | 99.19 |
| + density | 37.63 | 363 | 684 | 970 | 143 | 99.08 |
| + eigenvalue + density | 36.68 | 302 | 570 | 802 | 198 | 99.25 |
| + cumulative LDOS (ours, 3 seeds) | 36.64 | 291 | 582 | 809 | 168 | 99.24 |
| WANet | ||||||
| pretrained | 40.07 | 335 | 1454 | 1684 | 288 | 98.98 |
| + WALoss (3 seeds) | 41.00 | 331 | 1015 | 1296 | 156 | 99.13 |
| + density | 40.21 | 324 | 823 | 1101 | 140 | 99.22 |
| + eigenvalue + density | 40.25 | 296 | 560 | 775 | 138 | 99.23 |
| + cumulative LDOS (ours, 3 seeds) | 40.16 | 286 | 580 | 800 | 137 | 99.23 |
The combination is on par with ours, as the analysis predicts: its two terms are the two projections of . It has the lower LUMO and gap errors, with the gap within about two of our seed standard deviations. Ours has the lower HOMO and occupied-orbital errors, with the HOMO lower by more than two of our seed standard deviations on every backbone. Both are far ahead of WALoss, and ours beats WALoss on every metric and backbone by more than the two seed spreads combined. What the cumulative LDOS adds is that it reaches this point with one term, while the combination needs a ratio between its two weights and an index pairing of predicted and reference eigenvalues.
The variation you point out for density-only has one source: molecules whose predicted frontier orbital is the wrong orbital (overlap with the reference HOMO, LUMO or LUMO+1 below 50%). In the pretrained QHNet these are 8.2% of the test molecules, and they carry 79% of its mean gap error, about 100 mHa each. Any loss that reads the spectrum in the energy window removes them, density matching included, so on QHNet density-only lands close to ours in the mean. On the remaining molecules density matching barely changes the gap error (−9% / −4% / +5% on QHNet / SPHNet / WANet), whereas ours lowers it by about a fifth on all three (−19% / −22% / −23%). SPHNet and WANet have far fewer such molecules (0.6–0.8%), so there the difference shows in the mean. The new Appendix G.7 gives this explanation. (The 2027 Ha in the submitted paper is the run with w = 30. With w = 100, the weight used on the other QHNet splits, three seeds give 1868 ± 50. Table 1 now reports the w = 100 runs, and Table 9 reports both weights.)
Response to Reviewer EXdn - Part 3/3
W3: "The theoretical guarantees need to be separated from the properties of the sampled loss. [...] Proposition B.7 likewise does not establish that the increase in matrix error must be small."
Agreed on both. Next to Theorem 3.5 we now state its conditions. Identifiability and the absence of blind sectors hold for the continuous representation. At 256 points and 64 energies some directions are not resolved, mainly couplings between occupied orbitals and virtual orbitals above the window (Appendix B.3 measures them). The restoring-force bound assumes a single displaced level and a finite window. The unresolved directions are what the element-wise term supervises: removing it lowers the frontier errors further but multiplies the matrix error by 19 on QHNet and by 2.4–3.1 on SPHNet and WANet (see our response to WCpw). Proposition B.7 shows that a small increase of the matrix error is possible, not that it must be small. The observed change, at most +0.22% over the 12 settings (3 seeds), is now presented as an empirical result (Appendix B.4).
W4: "The empirical scope and uncertainty remain limited."
- Seeds. All main comparisons now have three seeds (72 runs), reported as mean ± standard deviation in Tables 1 and 6. Ours has the lower mean gap error than WALoss in all 12 backbone × split settings, by more than one seed standard deviation in each. The smallest margin is WANet stable-ood (528 ± 18 vs. 575 ± 2 Ha).
- A more recent predictor. We added QHFlow (Kim et al., 2025), a flow-matching model whose matrix error on stable-id (23 Ha) is a third of QHNet's, on all four splits (one seed, fine-tuned from the official checkpoints on the stable splits and from a pretraining with the official recipe on the dynamic splits). Our loss lowers its gap error on every split, by 12–42%, and is better than WALoss on three of the four (WALoss is better on dynamic-geo). On stable-id it leaves only 1 molecule with a wrong LUMO, against 18 for the official checkpoint and 9 after WALoss. QHFlow is in Table 1 and Figure 2, and its settings are in Table 18.
- Larger molecules and new elements. DFT (up to 62 atoms, with S, Cl and Br, at B97X-D), detailed in our response to kmdt (Q3): the released QHNet has the wrong frontier orbitals for every test conformer, which element-wise fine-tuning and WALoss do not repair and our loss repairs for most of them (new Appendix G.9).
- Periodic and SOC Hamiltonians are outside our scope: in metals there is no gap, so the energy window and the Fermi-level slice need a finite-temperature form. We state this as a limitation (Appendix I).
- Cost. Per fine-tuning step the term adds 49% (0.72 s on QHNet). Over the 30k fine-tuning steps this is about 5% of the cost of the 300k-step pretraining, and inference is unchanged. We now give both numbers (Sec. 4.1 and Appendix G.6).
- SCF. Agreed: the loss does not improve the SCF initial guess. This follows from the analysis: an initial guess uses only the occupied subspace (sector B), which the pretrained models already predict well, while our gains are in the orbital energies and the frontier orbitals. We present SCF acceleration as unchanged and the practical case as resting on the single-shot properties (Appendix G.5).
Thank you for the responses, whcih address most of my concerns. Overall, I keep my ratings.
Response to Reviewer EXdn - Part 1/3
Thank you for the careful review, including the code. We answer your three questions, then the weaknesses.
The Euclidean cosine of the coefficient vectors. This is the definition of the QH9 benchmark, computed by the official evaluators of QHNet and SPHNet/WANet that produced every reported value, and the supplied
metrics.pyreproduces it. The overlap formula in Appendix E is our error and is now corrected there. With the overlap metric the values rise by up to 1.6 points and the ranking of the methods is unchanged (QHNet, stable-id: pretrained 97.85%, WALoss 98.02%, ours 98.61%).Yes. In the script that produced Table 12 the timer starts before the forward pass and stops after the generalized eigensolve and the construction of the initial density matrix, so
t_infcontains all three. The suppliedscf_init.pywas a simplified re-implementation that left the eigensolve outside its timer. Appendix F now states what the timer covers.We added this discussion to Related Work (Sec. 5), and we now state the finite-sampling and energy-window conditions next to the main theorem (W3 below).