Pith.

Materials Science · arXiv:2610.01036 v1 · submitted 1 Oct 2026 · 68 references

Train for Accuracy, Execute at Scale: Architecture-Preserving Inference for Equivariant Atomistic Foundation Models

Lei Fu, Zihui Feng, Yongheng Li, Hongwei Du, Xin He, Junyi Wu, Kejie Bao, Yueyu Zhang

show 3 more authors

Zeyu Deng, Ziheng Lu, Bonan Zhu

The paper says

“Equivariant atomistic foundation models provide broadly transferable interatomic potentials trained against quantum-mechanical reference data, but their repeated execution at simulation scale remains computationally and memory intensive.”

more of the abstract

We present Symmetrix-XL, an inference engine that scales pretrained MACE checkpoints without retraining, distillation, or modification of their learned weights. It combines streamed-edge execution to avoid graph-wide materialization of expanded edge intermediates, model-specialized code generation to compile checkpoint-specific operators, and tiled execution to reuse a bounded device-memory workspace. On complete LAMMPS-step benchmarks, Symmetrix-XL reduces inference time by 3.1-5.0 times relative to ML-IAP + cuEquivariance across tested A100 and RTX 5090 workloads. On a single A100 80 GB GPU, the tested MACE-OMAT-0 capacity boundary increases from 24,565 atoms to 11.24 million atoms. This substantially lowers the hardware threshold for simulations that would otherwise require spatial decomposition across many GPUs and compute nodes. The same backend weak-scales to 703 million atoms on 64 A800 GPUs at 93.8 percent efficiency. Energy, force, stress, molecular-dynamics stability, and Matbench Discovery evaluations reproduce reference MACE behavior within measured tolerances. Case studies spanning solid-state, interfacial, and reactive systems demonstrate the increased capacity in realistic workflows. These results establish post-training execution as a scaling axis complementary to model redesign, compression, and distributed scale-out, and show that the practical accuracy-cost frontier depends on both model architecture and inference execution.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 2 Oct 2026 · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

Holds up. A genuinely solid systems paper: the integration and the measured results are new, honestly reported, and the one real soft spot—thin OMAT-0 float32 fidelity coverage at the scale the headline numbers actually claim—is acknowledged and does not break the central thesis. This line is wrong

2 major objections · 6 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the 68 references say.

The paper says, at Abstract and §7.5

The review did not quote this passage.

Pith says: Objection 1 of 2 · major

The sentence "Energy, force, stress, molecular-dynamics stability, and Matbench Discovery evaluations reproduce reference MACE behavior within measured tolerances" (b6) is not scoped to the configurations actually verified. The end-to-end fidelity battery in §7.5, Table 2, and Appendix A is almost entirely MACE-MPA-0 medium in float64; for the checkpoint and precision used in the headline throughput and capacity numbers (MACE-OMAT-0 medium, …

more of objection 1

… float32), the reference comparison is a single 5,000-atom SrTiO3 task (energy 1.2e-5 eV/atom, max |F| 6.53e-5 eV/A, stress 8.82e-8 eV/A^3) plus an NVE drift comparison on the same structure. Because the radial-spline gate in Appendix B is explicitly checkpoint-specific (worst internal derivative error 7.23e-3 in internal learned units, with physical fidelity assessed only by end-to-end tests), the preservation guarantee as advertised at 1.25–11.24 million atoms is an extrapolation from one chemistry and one structure. This is not an internal inconsistency, and the paper is transparent about the per-checkpoint nature of the gate, but the unqualified abstract phrasing overstates the coverage. I recommend either adding float32 OMAT-0 parity checks on one or two additional chemistries (the Li–Al, Li6PS5Cl, or OFF23 systems already used in case studies would be cheap) or explicitly restricting the fidelity sentence to the tested configurations.

The paper says, at §7.2 / Table 1

The review did not quote this passage.

Pith says: Objection 2 of 2 · major

The capacity-boundary timings in Table 1 each correspond to a different system size, and the paper states this clearly, but the headline comparison of tiled versus standard streaming at their respective capacity boundaries ("increases the per-atom Loop time by approximately 4% ... while accommodating approximately nine times as many atoms") conflates a tiling-effectiveness claim with a capacity claim.

more of objection 2

A reader could take the 4% overhead as a same-size tiling cost; it is not, since the tiled run operates at ~9× the atom count. The authors disclose this in the caption, but the §7.2 text should state equally prominently that a matched-size comparison of the two streaming modes is not reported anywhere in the paper.

6 minor objections

The paper says, at References

Pith says: minor objection 1 of 6

Several references are listed twice under different numbers: [10] duplicates [2], [12] duplicates [39], [28] duplicates [23], and [34] duplicates [24]. These should be consolidated to avoid citation clutter.

The paper says, at Figure 9 caption

Pith says: minor objection 2 of 6

The caption labels two panels as "(e)" (panels labelled e in the figure legend and in the sentence about DPn/DPw); one of the panel identifiers should be re-lettered for consistency with the in-text references.

show 4 more

The paper says, at §8.1

Pith says: minor objection 3 of 6

The sentence "Fig. 6 shows the four sample cells; Fig. 6 resolves the 10M grain-boundary network at true atomic scale" cites the same figure twice; the second reference should point to the specific panel (Fig. 6b) to avoid ambiguity.

The paper says, at §7.1 / Figure 2a

Pith says: minor objection 4 of 6

The ASE comparison uses an exact 6.0 A graph for PyTorch and a retained 6.5 A effective-cutoff graph for Symmetrix-XL. This asymmetry is disclosed in the caption and is conservative (it loads more edges onto Symmetrix-XL), but the main text should state the conservatism explicitly so readers do not treat the matched-LAMMPS claim as applying unchanged to the ASE boundary.

The paper says, at §7.2

Pith says: minor objection 5 of 6

Tiled streaming uses a fixed 8,192-workspace-receiver parameter, which appears to be a free design choice. A sentence reporting the sensitivity of capacity and per-atom Loop time to this parameter (or stating that results were insensitive over a tested range) would strengthen the claim that tiling is robust.

The paper says, at Throughout

Pith says: minor objection 6 of 6

Subscripts and superscripts are rendered inconsistently in running text (SrTiO3, Å3, cm2/s, eV/Å3, 10^4). This is likely a typesetting issue, but the camera-ready version should enforce uniform formatting of chemical formulae and units.

What would settle it

Run a fidelity sweep for MACE-OMAT-0 medium in float32: compare Symmetrix-XL against mace-torch on ~200 randomly sampled MP/WBM structures spanning >25 elements and varied coordination (including stretched and near-transition-state geometries), reporting max energy-per-atom, max force-component, and max stress-component differences. Separately re-run the Appendix B spline gate for this checkpoint and precision at 256 nodes and report the worst internal derivative error in force units via an end-to-end atomic-force comparison. Pass criterion: max |ΔF| consistent with the 6.53e-5 eV/A SrTiO3 result (within ~1e-3 eV/A) and spline gate acceptance. If deviations degrade on any chemistry, the abstract's blanket fidelity claim needs a precision/checkpoint qualifier.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 2 Oct 2026

  1. Reader holds up confidence high
  2. Skeptic partly agrees 54 s · 31,412 tokens read, 6,884 written
  3. Editor wrote the verdict above 18 s · 32,504 tokens read, 2,392 written
  4. Referee minor revision: 2 major objections, 6 minor 36 s · 31,799 tokens read, 5,262 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

Worth your time. This is a well-executed systems contribution, not a modeling paper, and it does not pretend otherwise. The three mechanisms are individually grounded in cited prior work—streamed-edge execution is the Sobek formulation [49], the specialization program extends Tan/Witt [33,34], tiling is a bounded-memory extension—so the novelty is the integration on top of Symmetrix plus the measured results: 11.24M atoms on one A100 versus the 24.5k baseline, 3.1–5.0x LAMMPS speedup, 703M atoms weak-scaling at 93.8%. Those numbers are mutually consistent between abstract and body, which is more than you usually get.

What it does well: the benchmark protocol is careful. Five warm-up, 20 measured steps, medians over fresh processes, zero neighbor-rebuild requirement enforced, capacity boundaries reproduced twice. The graph-construction asymmetry in the ASE comparison (6.0 Å exact for PyTorch, 6.5 Å retained skin for Symmetrix-XL) is disclosed, and it cuts against Symmetrix-XL by adding edges, so it is conservative. Fidelity is checked against genuinely external published results—Matbench Discovery, published MACE-MPA-0 workflows—not against quantities the paper defines, so the circularity burden is low. And the limitations section is unusually honest: capacity probes explicitly flagged as not sustained MD [b410], platform dependence, single-trajectory case studies.

The stress-test note is right about the one real soft spot: the fidelity battery is almost all MACE-MPA-0 float64, while the checkpoint and precision behind the headline capacity numbers is MACE-OMAT-0 float32. For that regime the end-to-end evidence is one 5,000-atom SrTiO3 task plus an NVE comparison. The spline gate is per-checkpoint and per-precision, and the reported worst derivative error (7.23e-3) is in internal learned units, so physical force impact is pointwise, not assumed. That means the preservation guarantee at 1.25–11.24M atoms across the varied chemistries in the case studies rests on extrapolation from a thin base. But it is not a fatal gap: the SrTiO3 spot check shows errors orders below physically meaningful thresholds, the spline qualification is per-checkpoint by design, and the case studies themselves concede internal-only validation where it applies. I would ask for one more OMAT-0 float32 fidelity point at genuinely large scale—say a million-atom energy/force comparison against the reference, or matched sustained MD—before banking on the blanket claim. I would not block the paper on it.

Who it is for: anyone deploying equivariant atomistic foundation models and anyone working on the accuracy-cost frontier of MLIP inference. It deserves a serious referee; accept with the fidelity-coverage refinement in mind.

The strongest objection

The architecture-preserving claim has two parts: an algebraic reassociation (streamed edges, §3) that is exact, and a radial-spline projection (Appendix B) that is a genuine approximation whose gate tolerances are checkpoint- and precision-specific. The measured worst derivative error of 7.23e-3 (Appendix B) is in internal learned units, so its physical force impact must be verified pointwise, not assumed. The fidelity battery in §7.5 and Appendix A is nearly all MACE-MPA-0 medium in float64: WBM relaxation/discovery, thermal conductivity, 87 diatomic pairs, DynaMat, all MPA-0. For the checkpoint and precision actually used in the headline throughput and capacity numbers — MACE-OMAT-0 medium, float32 — the end-to-end evidence is one SrTiO3 5,000-atom task (energy 1.200e-5 eV/atom, max |F| 6.53e-5 eV/A, §7.5) plus an NVE drift comparison on the same structure. The abstract's claim that 'Energy, force, stress ... reproduce reference MACE behavior within measured tolerances' is therefore asserted over a coverage region (OMAT-0 float32 at 1.25–11.24 M atoms, varied chemistries such as the Li–Al, SEI, and Au–Sn case studies) where no reference comparison exists. This is not an internal inconsistency: the spline gate is per-checkpoint and the SrTiO3 spot check shows errors orders below physically meaningful thresholds. But the preservation guarantee at the advertised scale rests on extrapolation from that thin base, and the paper's own case studies concede internal-only validation (b391). The recent optimized-deployment literature (refs 33–34) also means the magnitude of the 3.1–5.0x speedup is baseline-dependent; that is disclosed (§7, Fig. 2 caption) and conservative in direction, so it does not threaten the central thesis.

The reader identified fidelity generalization from the finite test battery to untested downstream observables as the weakest assumption. My stress-test sharpens that to a more concrete and checkable gap: the fidelity battery is essentially MPA-0 float64, while the headline throughput, capacity, and scaling claims are OMAT-0 medium float32; only one SrTiO3 config in float32 is checked end-to-end, and the flagship 11.24M-atom scale and the case-study chemistries have no reference comparison. This is load-bearing for the abstract's blanket fidelity sentence specifically, and it is testable with a bounded computational sweep. I nevertheless recommend UNCHANGED because (i) the §3 streamed reassociation is algebraically exact and the spline is a per-checkpoint, gated approximation with documented error bounds; (ii) the one float32 OMAT-0 check shows errors ~1e-5–1e-4 in physical units, orders below physically meaningful thresholds; (iii) the 6.0 vs 6.5 A graph asymmetry disclosed in Fig. 2 penalizes, not favors, Symmetrix-XL, so the speedup claim is conservative; and (iv) the paper is unusually explicit about capacity-probe, single-trajectory, internal-validation, and platform-dependence limits (b79, b214, b391, b410). No internal inconsistency or algebraic error was found. The suggested sweep is a verification step, not evidence of a defect.

The referee's report

If the results hold, the paper establishes post-training execution as a genuine third scaling axis for atomistic foundation models, complementary to architecture redesign and distillation, requiring no retraining or weight changes. The engineering claims are well evidenced: the benchmark protocol (§6) is unusually careful (five warm-up steps, 20 measured steps, three fresh-process trials, medians, zero neighbor-list-rebuild requirement, twice-reproduced capacity boundaries), the comparisons use matched checkpoints, coordinates, precision, and properties, and the distributed-scaling numbers are internally consistent with the reported atom-per-GPU counts. The fidelity checks validate against external published workflows and the reference mace-torch implementation rather than against paper-defined quantities, and the numerical agreement in Table 2 is quantitatively close (e.g., WBM discovery F1 0.835664 vs 0.835569; diatomic MAE 5.67e-6 eV/dimer). The paper is also unusually honest about its own limitations, repeatedly scoping case-study conclusions as single-trajectory or internally validated.

Pith's reading of the paper (a machine's summary, not the authors')

This paper tries to establish that post-training execution is a third scaling axis for atomistic foundation models, alongside designing cheaper architectures and distilling to smaller models. Its claim is that a fixed, pretrained MACE checkpoint runs dramatically faster and on far more atoms per GPU when only the inference engine changes—streamed edge processing, compiled checkpoint-specific operators, and bounded tiled workspaces—with the learned weights untouched. If the claim holds, the hardware threshold for million-atom simulations drops sharply, and dedicated inference backends become a practical lever that can be combined with model redesign and compression. The novelty is not a new architecture but evidence about how much of the accuracy–cost frontier is determined by execution rather than by the model itself.

What carries the argument. The central object is a reassociation of the equivariant message-passing contraction. Each expanded edge weight is written as a projection of a compact radial embedding, $W_{e,\pi a} = \sum_q \varphi_{eq} B_{q,\pi a}$, and the receiver message $m_i = \sum_{e:r(e)=i} \sum_{\pi,a} W_{e,\pi a} T_{\pi a}(h_{s(e)}, Y_e)$ is formed by generating each contribution near its point of use, accumulating it into the receiver, and discarding it. This cuts persistent graph-dependent storage from $\mathcal{O}(E C P) + \mathcal{O}(E W_R) + \mathcal{O}(N C G)$ to $\mathcal{O}(E K_{\mathrm{geom}}) + \mathcal{O}(N C K_{\mathrm{node}}) + \mathcal{O}(K_{\mathrm{work}})$, i.e. graph-plus-node state with a bounded kernel-local workspace, with the reverse pass recomputing radial and angular factors under a chosen schedule. The same streamed schedule is combined with code generation that bakes the checkpoint's fixed sparse coupling structure into compiled CPU or GPU kernels, and with tiled execution that partitions receivers and incident edges into bounded tiles so the large temporary workspaces are tile-sized rather than graph-sized.

Core claim. The paper's central claim is that an already-trained equivariant atomistic foundation model can be scaled at execution time instead of at training or architecture time. Symmetrix-XL keeps the MACE checkpoint's learned weights and architectural contract unchanged and replaces how the fixed inference program executes: expanded edge contributions are formed, accumulated into their receiver, and discarded rather than materialized graph-wide; the checkpoint's fixed sparse Clebsch–Gordan paths, coefficients, and layouts are compiled into model-specific kernels; and receivers can be partitioned into bounded tiles that reuse a fixed device-memory workspace. On complete LAMMPS steps the backend is 3.1 to 5.0 times faster than the ML-IAP with cuEquivariance baseline, lifts the single-A100 capacity for MACE-OMAT-0 from 24,565 to 11,240,455 atoms, and weak-scales to 703 million atoms on 64 A800 GPUs at 93.8 percent efficiency. Energy, force, stress, NVE conservation, thermal conductivity, and Matbench Discovery results all reproduce the reference mace-torch behavior within the stated tolerances, although the implementations are not bitwise identical.

The premise it rests on. The claim that unchanged weights give reference behavior rests on the fidelity of streamed, reordered contractions and radial-spline interpolation to genuine MACE outputs, verified only on the finite battery of tested systems and checkpoints; an untested observable or checkpoint more sensitive than the aggregate metrics could deviate beyond tolerance.

If the paper is right (Pith's inferences, not the authors')

Million-atom molecular dynamics becomes feasible on a single consumer GPU: tiled streaming reaches 4.15 million atoms on one RTX 5090 and an estimated 1.7–2.9 million on 16 and 24 GB devices, respectively, for the tested workload.

Distributed LAMMPS runs gain larger local domains per rank, since tiled streaming weak-scales to 703 million atoms on 64 A800 GPUs, lowering the minimum GPU count for a given system.

Dedicated inference backends join architecture redesign and distillation as a third lever on the accuracy–cost frontier, and the three can be combined since each leaves the deployed model untouched in different ways.

The streaming, specialization, and tiling principles are claimed to extend to other equivariant graph neural networks whose operators admit compatible schedules, subject to per-architecture implementation and numerical qualification.

The disclosed graph-construction asymmetry—6.0 Å exact for PyTorch versus a 6.5 Å effective cutoff with a retained 0.5 Å skin for Symmetrix-XL—means part of the end-to-end speedup may come from trading a slightly larger effective cutoff against fewer neighbor-list rebuilds; a matched-cutoff benchmark would isolate the pure model-evaluation gain.

A natural extension is distributing tiled execution across devices within a node, since tiling already partitions receivers; whether tiles can map across GPUs without the graph-wide $H_1$ state would determine if tiled capacity composes with scale-out.

The spline approach that holds at 256 nodes with worst internal derivative error $7.23\times10^{-3}$ suggests the same project-onto-spline trick could be pushed to fewer nodes for other models, trading measurable accuracy for further memory and speed.

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Equivariant atomistic foundation models provide broadly transferable interatomic potentials trained against quantum-mechanical reference data, but their repeated execution at simulation scale remains computationally and memory intensive. We present Symmetrix-XL, an inference engine that scales pretrained MACE checkpoints without retraining, distillation, or modification of their learned weights. It combines streamed-edge execution to avoid graph-wide materialization of expanded edge intermediates, model-specialized code generation to compile checkpoint-specific operators, and tiled execution to reuse a bounded device-memory workspace. On complete LAMMPS-step benchmarks, Symmetrix-XL reduces inference time by 3.1-5.0 times relative to ML-IAP + cuEquivariance across tested A100 and RTX 5090 workloads. On a single A100 80 GB GPU, the tested MACE-OMAT-0 capacity boundary increases from 24,565 atoms to 11.24 million atoms. This substantially lowers the hardware threshold for simulations that would otherwise require spatial decomposition across many GPUs and compute nodes. The same backend weak-scales to 703 million atoms on 64 A800 GPUs at 93.8 percent efficiency. Energy, force, stress, molecular-dynamics stability, and Matbench Discovery evaluations reproduce reference MACE behavior within measured tolerances. Case studies spanning solid-state, interfacial, and reactive systems demonstrate the increased capacity in realistic workflows. These results establish post-training execution as a scaling axis complementary to model redesign, compression, and distributed scale-out, and show that the practical accuracy-cost frontier depends on both model architecture and inference execution.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-10-02

The authors' main claim, as the classifier picked it out 1.00

“These results establish post-training execution as a scaling axis complementary to model redesign, compression, and distributed scale-out, and show that the practical accuracy-cost frontier depends on both model architecture and inference execution.”

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.06 · states limitation 0.18 · human participants 0.01 · controlled comparison 0.90 · randomized assignment 0.01 · states quantitative result 0.99 · compares with prior results 0.97 · mentions code or data availability 0.04

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Equivariant atomistic foundation models provide broadly transferable interatomic potentials trained against quantum-mechanical reference data, but their repeated execution at simulation scale remains computationally and memory intensive. background 0.96 0.07 0.03 asserted 1.00
We present Symmetrix-XL, an inference engine that scales pretrained MACE checkpoints without retraining, distillation, or modification of their learned weights. contribution 0.99 0.94 0.12 asserted 1.00
It combines streamed-edge execution to avoid graph-wide materialization of expanded edge intermediates, model-specialized code generation to compile checkpoint-specific operators, and tiled execution to reuse a bounded device-memory workspace. method 0.99 0.85 0.05 asserted 1.00
On complete LAMMPS-step benchmarks, Symmetrix-XL reduces inference time by 3.1-5.0 times relative to ML-IAP + cuEquivariance across tested A100 and RTX 5090 workloads. result 1.00 0.95 0.14 asserted 1.00
On a single A100 80 GB GPU, the tested MACE-OMAT-0 capacity boundary increases from 24,565 atoms to 11.24 million atoms. result 1.00 0.94 0.09 asserted 1.00
This substantially lowers the hardware threshold for simulations that would otherwise require spatial decomposition across many GPUs and compute nodes. interpretation 0.99 0.70 0.08 asserted 0.99
The same backend weak-scales to 703 million atoms on 64 A800 GPUs at 93.8 percent efficiency. result 1.00 0.94 0.07 asserted 1.00
Energy, force, stress, molecular-dynamics stability, and Matbench Discovery evaluations reproduce reference MACE behavior within measured tolerances. result 1.00 0.93 0.07 asserted 1.00
Case studies spanning solid-state, interfacial, and reactive systems demonstrate the increased capacity in realistic workflows. result 0.75 0.92 0.04 asserted 1.00
These results establish post-training execution as a scaling axis complementary to model redesign, compression, and distributed scale-out, and show that the practical accuracy-cost frontier depends on both model architecture and inference execution. interpretation 1.00 0.81 0.87 asserted 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from simulation or computation 0.82

What was examined, and what was not

Sources read

  • arXiv listing abstract v1

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-10-02: 1 request, 7,747 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (15)
Figure 1 of the paper
Figure 1. Overview of the Symmetrix-XL execution strategy.
Figure 2 of the paper
Figure 2. End-to-end inference time; lower values are better.
Figure 3 of the paper
Figure 3. Single-GPU SrTiO3 LAMMPS capacity for MACE-OMAT-0 medium in float32 on a, one A100 80 GB and b, one RTX 5090 32 GB. Bars show the largest successful system on the logarithmic atom-count scale. Each boundary was reproduced twice in fresh processes with a 6.0 Å model cutoff and a 0.5 Å neighbor skin. The A100 largest successes are 24,565, 1,250,235, and 11,240,455 atoms for ML-IAP with cuEquivariance, standard streaming, and tiled streaming, respectively; the corresponding RTX 5090 values are 8,640, 486,680, and 4,152,920 atoms
Figure 4 of the paper
Figure 4. CPU inference time for MACE-OMAT-0 medium on 5,000-atom cubic SrTiO
Figure 5 of the paper
Figure 5. Distributed scaling of moving-NVT MACE-OMAT-0 medium LAMMPS simulations on A800-SXM4-80GB
Figure 6 of the paper
Figure 6. (a) The four sample cells of the scale series (same 24-grain construction, Li green, Al silver). Left to right / top to bottom: 20k, 100k, 1M, and 10M atoms. The 1M and 10M panels show a uniformly subsampled subset of atoms (1/5 and 1/50, display radii rescaled for legibility); the 20k and 100k panels show every atom. The 10M cell edge (548 Å) is 7.9× the 20k edge at identical composition and grain count. (b) True-scale 4 Å-thick slice through the 10M cell (z ∈ [270, 274] Å, 73,005 atoms). Left: element coloring showing differently oriented grains and disordered boundary atoms.…
Figure 7 of the paper
Figure 7. Lithium transfer and spatially resolved vibrational spectra at the
Figure 8 of the paper
Figure 8. Shock-driven decomposition of a 201 600-atom β-HMX crystal (MACE-OFF23; 98.5 × 173.4 × 108.0 Å 3 at t = 0) driven by a travelling wave (0.15 eV/Å, 20 Å/ps, λ = 5 Å) at 600 K under NPH conditions (P0 = 0). (a–e) Chemical-damage maps at t = 0.25, 5, 10, 15, and 20 ps; each panel shows a slab of the cell (fractional x < 0.06) spanning the full instantaneous y–z cross-section, with the propagation direction z horizontal. Grey denotes intact HMX molecules; red denotes decomposition fragments and products classified from the bond graph. Each panel is drawn at its own instantaneous cell…
Figure 9 of the paper
Figure 9. Ring-opening polymerization and S–S crosslinking in an approximately 200k-atom thiirane liquid containing
Figure 10 of the paper
Figure 10. (a) Full-cell architecture (schematic render, lower four-phase stack: Li metal slab | mosaic inorganic layer | LEDC organic layer | liquid electrolyte; the top mirror half is omitted for clarity). Grey = Li metal; dark blue = LiF grains; dark orange = Li2O grains; purple = Li2CO3 grains (43 grains per mosaic layer); green = LEDC organic SEI; teal = liquid electrolyte (EC:DMC + 1.2 M LiPF6). (b) Column-resolved contact analysis of the relaxed Li | mosaic interfaces. Top: gap evolution; middle: interfacial column contact maps (green = contact column, red = void column) — the…
Figure 11 of the paper
Figure 11. (a) DLi(z) profile (in-plane Dxy and 3D D3D conventions) with four-zone shading; the dotted line marks the fast-transport corridor (z = 50–145 Å). (b) spatial mobility map. (c) Liquid-band Li first-shell RDF. (d) Microenvironment mobility ladder. (e) Spanning-probability threshold scan (step function) with the D∗ crit confidence band (orange, 3.72(+1.39/-1.27)×10−7 cm2 /s) and the chain-level point estimate (black dashed). (f) Fast-ion volume fraction and largest-connected-cluster fraction vs. threshold percentile. 18
Figure 12 of the paper
Figure 12. Transport simulations and system-size scaling in polycrystalline Li6PS5Cl with MACE-MP small and Symmetrix-XL. (a) Normalized Li+ flux distribution in Li6PS5Cl with 50% anion disorder at 300 K and a grain size of approximately 25 nm. The colour scale shows the local Li+ flux magnitude divided by the imposed concentration difference, |q|/∆c. The inset enlarges the grain interiors and adjacent grain-boundary region. (b) Li+ diffusion activation energies in the bulk and grain boundaries as a function of anion disorder. Filled symbols show MD results obtained with the MACE-MP small…
Figure 13 of the paper
Figure 13. Structural and diffusive evolution of the liquid Au–Sn alloy/solid Au interface. (a) Initial interfacial model
Figure 14 of the paper
Figure 14. collects complementary checks spanning model outputs, molecular-dynamics stability, the spline approxi￾mation used by the evaluator, and a downstream phonon workflow. These checks test different parts of the execution path and are not interchangeable: the diatomic curves measure agreement with published mace-torch results, the thermal-conductivity results compare both implementations with DFT references, the NVE trajectory tests conservation of a physical invariant, and the radial comparison measures interpolation of internal learned features. 1 2 3 4 5 Distance (Å) −10.0 −7.5 −5.0…
Figure 15 of the paper
Figure 15. MPI-only element scaling for the 4800-atom benchmark with OpenMP fixed to one thread. The combined figure contains the 1-, 5-, and 20-element systems across the tested MPI rank counts, with matched implementation and precision comparisons. Bars report time in µs/atom/step. Each case uses five warm-up steps followed by 20 measured NPT steps. The reported observable is the final measured time per atom per step; lower values indicate higher performance. The comparison includes FP32 and FP64 for both the original Symmetrix implementation and Symmetrix-XL

Figures are the authors', reproduced from the paper.

References (68)
  1. [49] Vsevolod Chorošajev and Cédric Bény. Sobek: Streaming equivariant tensor product convolutions.arXiv preprint arXiv:2607.18074, 2026 on PithPith's reviewarXiv
  2. [1] Janosh Riebesell, Rhys E. A. Goodall, Philipp Benner, Yuan Chiang, Bowen Deng, Gerbrand Ceder, Mark Asta, Alpha A. Lee, Anubhav Jain, and Kristin A. Persson. Matbench discovery: A framework to evaluate machine learning crystal stability predictions.Nature Machine Intelligence,... on Pith
  3. [3] Luis Barroso-Luque, Muhammed Shuaibi, Xiang Fu, Brandon M. Wood, Misko Dzamba, Meng Gao, Ammar Rizvi, Matt Uyttendaele, C. Lawrence Zitnick, and Zachary W. Ulissi. Open materials 2024 (OMat24) inorganic materials dataset and models.arXiv preprint arXiv:2410.12771, 2024 on PithPith's reviewarXiv
  4. [4] Brandon M. Wood, Misko Dzamba, Xiang Fu, Meng Gao, Muhammed Shuaibi, Luis Barroso-Luque, et al. UMA: A family of universal models for atoms.arXiv preprint arXiv:2506.23971, 2026 on PitharXiv
  5. [5] Kairos Materials. Prophet: Scaling atomistic foundation models across composition, configuration, and spin, 2026. Technical report on Pith
  6. [6] So Takamoto, Chikashi Shinagawa, Daisuke Motoki, Kosuke Nakago, Wenwen Li, Iori Kurata, Taku Watanabe, Yoshihiro Yayama, Hiroki Iriguchi, Yusuke Asano, Tasuku Onodera, Takafumi Ishii, Takao Kudo, Hideki Ono, Ryohto Sawada, Ryuichiro Ishitani, Marc Ong, Taiki Yamaguchi, Toshiki... on Pith
  7. [7] Chi Chen and Shyue Ping Ong. A universal graph deep learning interatomic potential for the periodic table. Nature Computational Science, 2:718–728, 2022. doi: 10.1038/s43588-022-00349-3 on Pithdoi:10.1038/s43588-022-00349-3
  8. [8] Bowen Deng, Peichen Zhong, KyuJung Jun, Janosh Riebesell, Kevin Han, Christopher J. Bartel, and Gerbrand Ceder. CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling. Nature Machine Intelligence, 5:1031–1041, 2023. doi: 10.1038/s4225... on Pithdoi:10.1038/s42256-023-00716-3
  9. [9] Kamal Choudhary, Brian DeCost, Lily Major, Keith Butler, Jeyan Thiyagalingam, and Francesca Tavazza. Unified graph neural network force-field for the periodic table: solid state applications.Digital Discovery, 2:346–355, on Pith
  10. [10] Ilyes Batatia, Philipp Benner, Yuan Chiang, Alin M. Elena, Dávid P. Kovács, Janosh Riebesell, et al. A foundation model for atomistic materials chemistry.The Journal of Chemical Physics, 163(18):184110, 2025. doi: 10.1063/5.0297006 on Pithdoi:10.1063/5.0297006
  11. [11] Han Yang, Chenxi Hu, Yichi Zhou, Xixian Liu, Yu Shi, Jielan Li, Guanzhi Li, Zekun Chen, Shuizhou Chen, Claudio Zeni, Matthew Horton, Robert Pinsler, Andrew Fowler, Daniel Zügner, Tian Xie, Jake Smith, Lixin Sun, Qian Wang, Lingyu Kong, Chang Liu, Hongxia Hao, and Ziheng Lu. Ma... on PithPith's reviewarXiv
  12. [13] Jaesun Kim, Jisu Kim, Jaehoon Kim, Jiho Lee, Yutack Park, Youngho Kang, and Seungwu Han. Data-efficient multifidelity training for high-fidelity machine learning interatomic potentials.Journal of the American Chemical Society, 147(1):1042–1054, 2025. doi: 10.1021/jacs.4c14455 on Pithdoi:10.1021/jacs.4c14455
  13. [14] Luis Barros-Luque, Muhammed Shuaibi, Xiang Fu, Brandon M. Wood, Misko Dzamba, Meng Gao, Ammar Rizvi, Matt Uyttendaele, C. Lawrence Zitnick, and Zachary W. Ulissi. The Open Materials 2024 (OMat24) inorganic materials dataset and models.Nature Computational Science, 6:642–652, 2... on Pith
  14. [15] Mark Neumann, James Gin, Benjamin Rhodes, Steven Bennett, Zhiyi Li, Hitarth Choubisa, Arthur Hussey, and Jonathan Godwin. Orb: A fast, scalable neural network potential. arXiv preprint arXiv:2410.22570, 2024. URL https://arxiv.org/abs/2410.22570 on PithPith's reviewarXiv
  15. [16] Benjamin Rhodes, Sander Vandenhaute, Vaidotas Šimkus, James Gin, Jonathan Godwin, Tim Duignan, and Mark Neumann. Orb-v3: atomistic simulation at scale. arXiv preprint arXiv:2504.06231, 2025. URL https: //arxiv.org/abs/2504.06231 on PithPith's reviewarXiv
  16. [17] Duo Zhang, Xinzijian Liu, Xiangyu Zhang, Chengqian Zhang, Chun Cai, Hangrui Bi, et al. DPA-2: a large atomic model as a multi-task learner.npj Computational Materials, 10:293, 2024. doi: 10.1038/s41524-024-01493-2 on Pithdoi:10.1038/s41524-024-01493-2
  17. [18] Duo Zhang, Anyang Peng, Chun Cai, Wentao Li, Yuanchang Zhou, Jinzhe Zeng, Mingyu Guo, Chengqian Zhang, Bowen Li, Hong Jiang, Tong Zhu, Weile Jia, Linfeng Zhang, and Han Wang. A graph neural network for the era of large atomistic models. arXiv preprint arXiv:2506.01686, 2025. U... on PitharXiv
  18. [19] Yury Lysogorskiy, Anton Bochkarev, and Ralf Drautz. Graph atomic cluster expansion for foundational machine learning interatomic potentials.npj Computational Materials, 12:114, 2026. doi: 10.1038/s41524-026-01979-1 on Pithdoi:10.1038/s41524-026-01979-1
  19. [20] Xiang Fu, Brandon M. Wood, Luis Barroso-Luque, Daniel S. Levine, Meng Gao, Misko Dzamba, and C. Lawrence Zitnick. Learning smooth and expressive interatomic potentials for physical property prediction. InProceedings of the 42nd International Conference on Machine Learning, vol... on Pith
  20. [21] Brandon M. Wood, Misko Dzamba, Xiang Fu, Meng Gao, Muhammed Shuaibi, Luis Barroso-Luque, Ka- reem Abdelmaqsoud, Vahe Gharakhanyan, John Kitchin, Daniel S. Levine, Kyle Michel, Anuroop Sriram, Taco S. Cohen, Abhishek Das, Sushree Sahoo, Ammar Rizvi, Zachary Ulissi, and Larry Zi... on Pith
show 48 more
  1. [22] Arslan Mazitov, Filippo Bigi, Matthias Kellner, Paolo Pegolo, Davide Tisi, Guillaume Fraux, Sergey Pozdnyakov, Philip Loche, and Michele Ceriotti. PET-MAD as a lightweight universal interatomic potential for advanced materials modeling.Nature Communications, 16:10653, 2025. do... on Pithdoi:10.1038/s41467-025-65662-7
  2. [25] Ting Liang, Ke Xu, Eric Lindgren, Zherui Chen, Rui Zhao, Jiahui Liu, Esmée Berger, Benrui Tang, Bohan Zhang, Yanzhou Wang, Keke Song, Penghua Ying, Nan Xu, Haikuan Dong, Shunda Chen, Paul Erhart, Zheyong Fan, Tapio Ala-Nissila, and Jianbin Xu. NEP89: Universal neuroevolution p... on PithPith's reviewarXiv
  3. [26] Zheyong Fan, Zezhu Zeng, Cunzhi Zhang, Yanzhou Wang, Keke Song, Haikuan Dong, Yue Chen, and Tapio Ala-Nissila. Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport.Physical Review B, 104:104... on Pithdoi:10.1103/physrevb.104
  4. [27] Zheyong Fan, Yanzhou Wang, Penghua Ying, Keke Song, Junjie Wang, Yong Wang, Zezhu Zeng, Ke Xu, Eric Lindgren, J. Magnus Rahm, Alexander J. Gabourie, Jiahui Liu, Haikuan Dong, Jianyang Wu, Yue Chen, Zheng Zhong, Jian Sun, Paul Erhart, Yanjing Su, and Tapio Ala-Nissila. GPUMD: A... on Pithdoi:10.1063/5.0106617
  5. [28] Teddy Koker, Mit Kotak, and Tess Smidt. Training a foundation model for materials on a budget.arXiv preprint arXiv:2508.16067, 2025 on PitharXiv
  6. [29] Yunyang Li, Lin Huang, Zhihao Ding, Chu Wang, Xinran Wei, Han Yang, Zun Wang, Chang Liu, Yu Shi, Peiran Jin, Tao Qin, Mark Gerstein, and Jia Zhang. E2Former: An efficient and equivariant transformer with linear-scaling tensor products.arXiv preprint arXiv:2501.19216, 2025. doi... on Pithdoi:10.48550/arxiv.2501.19216
  7. [30] Tiancheng Li, Jianming Xue, Linfeng Zhang, Duo Zhang, and Han Wang. Universal machine-learning molecular dynamics at the speed of empirical potentials.arXiv preprint arXiv:2608.19041, 2026. doi: 10.48550/arXiv.2608. 19041 on PithPith's reviewarXivdoi:10.48550/arxiv.2608.19041
  8. [31] Albert Musaelian, Simon Batzner, Anders Johansson, Lixin Sun, Cameron J. Owen, Mordechai Kornbluth, and Boris Kozinsky. Learning local equivariant representations for large-scale atomistic dynamics.Nature Communications, 14:579, 2023. doi: 10.1038/s41467-023-36329-y on Pithdoi:10.1038/s41467-023-36329-y
  9. [32] Sangmin Oh, Jinmu You, Jaesun Kim, Jiho Lee, Hyungmin An, Seungwu Han, and Youngho Kang. A lightweight universal machine-learning interatomic potential via knowledge distillation for scalable atomistic simulations. arXiv preprint arXiv:2604.10887, 2026 on PithPith's reviewarXiv
  10. [33] Chuin Wei Tan, Marc L. Descoteaux, Mit Kotak, Gabriel de Miranda Nascimento, Seán R. Kavanagh, Laura Zichi, Menghang Wang, Aadit Saluja, Yizhong R. Hu, Tess Smidt, Anders Johansson, William C. Witt, Boris Kozinsky, and Albert Musaelian. High-performance training and inference ... on Pithdoi:10.1039/d5dd00423c
  11. [34] Seán R. Kavanagh, Chuin Wei Tan, Menghang Wang, Marc L. Descoteaux, Gabriel de Miranda Nascimento, Ulrik Unneberg, Laura Zichi, Francesco Libbi, Norma Rivano, Austin Glover, Vivek Bharadwaj, Anders Johansson, William C. Witt, Albert Musaelian, and Boris Kozinsky. Fast and accu... on PithPith's reviewarXiv
  12. [35] Vivek Bharadwaj, Austin Glover, Aydın Buluç, and James Demmel. An efficient sparse kernel generator for O(3)-equivariant deep networks. InProceedings of the Platform for Advanced Scientific Computing Conference, on Pith
  13. [36] Seung Yul Lee, Hojoon Kim, Yutack Park, Dawoon Jeong, Seungwu Han, Yeonhong Park, and Jae W. Lee. FlashTP: Fused, sparsity-aware tensor product for machine learning interatomic potentials. InProceedings of the 42nd International Conference on Machine Learning, volume 267 ofPro... on Pith
  14. [37] Paul Fuchs, Weilong Chen, Stephan Thaler, and Julija Zavadlav. chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations.arXiv preprint arXiv:2506.04055, 2025 on PithPith's reviewarXiv
  15. [38] doi: 10.1137/1.9781611979084.3 on Pithdoi:10.1137/1.9781611979084.3
  16. [39] Yutack Park, Jaesun Kim, Seungwoo Hwang, and Seungwu Han. Scalable parallel algorithm for graph neural network interatomic potentials in molecular dynamics simulations.Journal of Chemical Theory and Computation, 20:4857–4868, 2024. doi: 10.1021/acs.jctc.4c00190. 25 Symmetrix-X... on Pithdoi:10.1021/acs.jctc.4c00190
  17. [40] Ilyes Batatia, Dávid Péter Kovács, Gregor N. C. Simm, Christoph Ortner, and Gábor Csányi. MACE: Higher order equivariant message passing neural networks for fast and accurate force fields. InAdvances in Neural Information Processing Systems, volume 35, pages 11423–11436, 2022 on Pith
  18. [41] William C. Witt. Symmetrix. GitHub repository, n.d. URL https://github.com/wcwitt/symmetrix. Accessed 29 September 2026 on Pith
  19. [42] Mario Geiger and Tess Smidt. e3nn: Euclidean neural networks.arXiv preprint arXiv:2207.09453, 2022 on PithPith's reviewarXiv
  20. [43] MACE developers. mace-torch. https://github.com/ACEsuit/mace, 2026. Reference PyTorch implementa- tion; accessed 11 September 2026 on Pith
  21. [44] Adam Paszke et al. PyTorch: An imperative style, high-performance deep learning library.Advances in Neural Information Processing Systems, 32:8024–8035, 2019 on Pith
  22. [45] Ask Hjorth Larsen et al. The atomic simulation environment—a python library for working with atoms.Journal of Physics: Condensed Matter, 29:273002, 2017. doi: 10.1088/1361-648X/aa680e on Pithdoi:10.1088/1361-648x/aa680e
  23. [46] Aidan P. Thompson, H. Metin Aktulga, Richard Berger, Dan S. Bolintineanu, W. Michael Brown, et al. LAMMPS – a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Computer Physics Communications, 271:108171, 2022. doi: 10.10... on Pithdoi:10.1016/j.cpc.2021.108171
  24. [47] NVIDIA. cuequivariance. https://github.com/NVIDIA/cuEquivariance, 2026. Software repository; accessed 11 September 2026 on Pith
  25. [48] Justin S. Smith. Enabling scalable AI-driven molecular dynamics simu- lations. NVIDIA Technical Blog, https://developer.nvidia.com/blog/ enabling-scalable-ai-driven-molecular-dynamics-simulations/ , 2025. Published 20 Octo- ber 2025; accessed 20 September 2026 on Pith
  26. [50] Anders Johansson, Evan Weinberg, Christian R. Trott, Megan J. McCarthy, and Stan G. Moore. LAMMPS- KOKKOS: Performance portable molecular dynamics across exascale architectures. InProceedings of the SC ’25 Workshops of the International Conference for High Performance Computin... on Pithdoi:10.1145/3731599.3767498
  27. [51] AMD. HIP runtime compilation. https://rocm.docs.amd.com/projects/HIP/en/latest/reference/ hip_runtime_api/modules/runtime_compilation.html, 2026. Documentation; accessed 11 September 2026 on Pith
  28. [52] Christian R. Trott et al. Kokkos 3: Programming model extensions for the exascale era.IEEE Transactions on Parallel and Distributed Systems, 33(4):805–817, 2022. doi: 10.1109/TPDS.2021.3097283 on Pithdoi:10.1109/tpds.2021.3097283
  29. [53] NVIDIA. CUDA runtime compilation API. https://docs.nvidia.com/cuda/nvrtc/, 2026. Documentation; accessed 11 September 2026 on Pith
  30. [54] Balázs Póta, Paramvir Ahlawat, Gábor Csányi, and Michele Simoncelli. Thermal conductivity predictions with foundation atomistic models.Nature Communications, 2026. doi: 10.1038/s41467-026-76391-w on Pithdoi:10.1038/s41467-026-76391-w
  31. [55] Xiang Fu, Zhenghao Wu, Wujie Wang, Tian Xie, Sinan Keten, Rafael Gomez-Bombarelli, and Tommi Jaakkola. Forces are not enough: Benchmark and critical evaluation for machine learning force fields with molecular simulations.Transactions on Machine Learning Research, 2023 on Pith
  32. [56] Filippo Bigi, Guillaume Fraux, Nicholas J. Browning, and Michele Ceriotti. Fast evaluation of spherical harmonics with sphericart.The Journal of Chemical Physics, 159:064802, 2023. doi: 10.1063/5.0156307 on Pithdoi:10.1063/5.0156307
  33. [57] W. C. Witt et al. symmetrix: A cross-platform evaluator for MACE models; Symmetrix-XL v0.1.1. https:// github.com/wcwitt/symmetrix and https://github.com/bonan-group/symmetrix-xl, 2026. Source commit e99fea0. The limgal checkpoint is distributed unchanged with the v0.1.1 relea... on Pith
  34. [58] J. Schiøtz, F. D. Di Tolla, and K. W. Jacobsen. Softening of nanocrystalline metals at very small grain sizes. Nature, 391:561–562, 1998 on Pith
  35. [59] P. Virtanen et al. SciPy 1.0: Fundamental algorithms for scientific computing in python.Nature Methods, 17: 261–272, 2020 on Pith
  36. [60] H. Van Swygenhoven, P. M. Derlet, and A. G. Frøseth. Stacking faults and microtwinning in nanocrystalline fcc metals.Nature Materials, 3:399–403, 2004. 26 Symmetrix-XLA PREPRINT on Pith
  37. [61] Dávid P. Kovács, J. Harry Moore, Nicholas J. Browning, Ilyes Batatia, John T. Horton, et al. MACE-OFF: Short-range transferable machine learning force fields for organic molecules.Journal of the American Chemical Society, 147(21):17598–17611, 2025. doi: 10.1021/jacs.4c07099 on Pithdoi:10.1021/jacs.4c07099
  38. [62] M. A. Meyers, A. Mishra, and D. J. Benson. Mechanical properties of nanocrystalline materials.Progress in Materials Science, 51:427–556, 2006 on Pith
  39. [63] Alejandro Strachan, Edward M. Kober, Adri C. T. van Duin, Jonas Oxgaard, and William A. III Goddard. Thermal decomposition of RDX from reactive molecular dynamics.The Journal of Chemical Physics, 122(5):054502, on Pith
  40. [64] Pierre Sigwalt. Stereoelection and stereoselection in the ring-opening polymerization of epoxides and episulfides. Pure and Applied Chemistry, 48(3):257–266, 1976. doi: 10.1351/pac197648030257 on Pithdoi:10.1351/pac197648030257
  41. [65] Giovanni Bussi, Davide Donadio, and Michele Parrinello. Canonical sampling through velocity rescaling.The Journal of Chemical Physics, 126(1):014101, 2007. doi: 10.1063/1.2408420. URL https://doi.org/10. 1063/1.2408420 on Pithdoi:10.1063/1.2408420
  42. [66] L. Martínez, R. Andrade, E. G. Birgin, and J. M. Martínez. PACKMOL: A package for building initial configura- tions for molecular dynamics simulations.Journal of Computational Chemistry, 30:2157–2164, 2009 on Pith
  43. [67] Yongliang Ou, Lena Scholz, Sanath Keshav, Yuji Ikeda, Marvin Kraft, Sergiy Divinski, Rafael Gómez-Bombarelli, Wolfgang G. Zeier, Felix Fritzen, and Blazej Grabowski. Microstructural insights into fast ion transport in solid electrolytes via multiscale modeling.Nature Communica... on Pithdoi:10.1038/s41467-026-76216-w
  44. [68] Luis Barros-Luque, Muhammed Shuaibi, Xiang Fu, Brandon M. Wood, Misko Dzamba, Meng Gao, Ammar Rizvi, Matt Uyttendaele, C. Lawrence Zitnick, and Zachary W. Ulissi. The open materials 2024 (OMat24) inorganic materials dataset and models.Nature Computational Science, 6:642–652, 2... on Pith
  45. [69] Roderic P. Quirk, Marissa Ocampo, Michael J. Polce, and Chrys Wesdemiotis. Functionalization of poly(styryl)lithium with thiiranes: Sulfur extrusion vs ring-opening mechanisms.Macromolecules, 40(7): 2352–2360, 2007. doi: 10.1021/ma0628026 on Pithdoi:10.1021/ma0628026
  46. [2005] doi: 10.1063/1.1831277 on Pithdoi:10.1063/1.1831277
  47. [2023] doi: 10.1039/D2DD00096B on Pithdoi:10.1039/d2dd00096b
  48. [2025] doi: 10.52202/085713-4310. URL https://papers.nips.cc/paper_files/paper/2025/hash/ bbf23e81b0ad7637fe9a731d0b676ca6-Abstract-Conference.html on Pithdoi:10.52202/085713-4310
Cited by 4 Pith papers

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment