Paper Citation Record · LEDGER

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs

As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2412.20796.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.20796 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T23:15:24.945850Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:13:41.132740Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-15T16:13:41.293622Z

Reference resolution

41 of 41 outbound references displayed

verified exact1
verified fuzzy32
unresolved7
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d994e61f-4f39-4c86-8b4d-d28b6669798f · outbound

This paper cites Scalable parallel algorithm for graph neural network interatomic potentials in molecular dynamics simulations,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Scalable parallel algorithm for graph neural network interatomic potentials in molecular dynamics simulations,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.607324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5344c197-3b20-4d84-b30b-e3e1f1cd17f1 · outbound

This paper cites A foundation model for atomistic materials chemistry.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs A foundation model for atomistic materials chemistry

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T23:15:24.776720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35f6926-aad6-4e48-b783-9d66fc590339 · outbound

This paper cites Chgnet as a pretrained universal neural network potential for charge-informed atomistic modelling,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Chgnet as a pretrained universal neural network potential for charge-informed atomistic modelling,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.593060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8ed59815-37d2-475b-b812-2ed852fe0074 · outbound

This paper cites Deepmd-kit: A deep learning package for many-body potential energy representation and molecular dynamics,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Deepmd-kit: A deep learning package for many-body potential energy representation and molecular dynamics,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.577481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ca5974e2-5b28-4734-98fe-b3203181581f · outbound

This paper cites Quantum-chemical insights from deep tensor neural networks,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Quantum-chemical insights from deep tensor neural networks,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.560818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4356dc9d-dde1-492e-bdb2-0eae3656a9e0 · outbound

This paper cites Schnet: A continuous-filter convo- lutional neural network for modeling quantum interactions,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Schnet: A continuous-filter convo- lutional neural network for modeling quantum interactions,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.548386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 39451e4b-c965-4562-80f9-5ca36d4adbdd · outbound

This paper cites Hierarchical modeling of molecular energies using a deep neural network,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Hierarchical modeling of molecular energies using a deep neural network,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.533388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ca98cfb7-f6b9-4883-83ff-2f2d3827e4a1 · outbound

This paper cites Physnet: A neural network for predicting energies, forces, dipole moments, and partial charges,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Physnet: A neural network for predicting energies, forces, dipole moments, and partial charges,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.520258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f3ed123d-e979-4039-9f68-b5acb47cc5b8 · outbound

This paper cites Directional message pass- ing for molecular graphs,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Directional message pass- ing for molecular graphs,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.507011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a81c9880-6eed-4576-871b-8e4415bf8df8 · outbound

This paper cites Mace: Higher order equivariant message passing neural networks for fast and accurate force fields,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Mace: Higher order equivariant message passing neural networks for fast and accurate force fields,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.493830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ace5d095-9588-4bd1-be61-0e3512da4211 · outbound

This paper cites Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.481161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 670a8396-7070-4388-8267-2da872a79e88 · outbound

This paper cites Gemnet: Universal di- rectional graph neural networks for molecules,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Gemnet: Universal di- rectional graph neural networks for molecules,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.465942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ded20530-0fd6-4e97-813b-450416d4c9cf · outbound

This paper cites Ani-1: an extensible neural network potential with dft accuracy at force field computational cost,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Ani-1: an extensible neural network potential with dft accuracy at force field computational cost,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.452161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e39ae3e0-3b75-4670-b1ad-9ded8e6e127e · outbound

This paper cites Extending the applicability of the ani deep learning molecular potential to sulfur and halogens,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Extending the applicability of the ani deep learning molecular potential to sulfur and halogens,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.437393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1156a720-1dc0-44b6-b3aa-b0c67644610b · outbound

This paper cites Generalized neural-network representation of high-dimensional potential-energy surfaces,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Generalized neural-network representation of high-dimensional potential-energy surfaces,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.422684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2ada07c6-5e92-4256-be6e-d4d1e127bf60 · outbound

This paper cites Embedded atom neural network poten- tials: Efficient and accurate machine learning with a physically inspired representation,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Embedded atom neural network poten- tials: Efficient and accurate machine learning with a physically inspired representation,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.410273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b8210c44-4685-42d9-b377-d8e07cbe3b47 · outbound

This paper cites Equivariant message passing for the prediction of tensorial properties and molecular spectra,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Equivariant message passing for the prediction of tensorial properties and molecular spectra,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.396487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eccdc498-a5fe-4c06-bd2c-ca8afdbd7b2b · outbound

This paper cites E (3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs E (3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T23:15:24.847946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c54bdf03-dc2c-44e1-96fa-3b7716d750bd · outbound

This paper cites Newtonnet: a newtonian message passing network for deep learning of interatomic potentials and forces,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Newtonnet: a newtonian message passing network for deep learning of interatomic potentials and forces,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.374057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d674b0d8-15f0-49b7-a95d-03335425ad1a · outbound

This paper cites Spookynet: Learning force fields with electronic degrees of freedom and nonlocal effects,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Spookynet: Learning force fields with electronic degrees of freedom and nonlocal effects,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.360670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cec64180-8790-4afc-8f84-6b25e4f56520 · outbound

This paper cites Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T23:15:24.860975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8650c8f2-11d6-45a7-bb01-9d04d901f13c · outbound

This paper cites A universal graph deep learning interatomic potential for the periodic table,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs A universal graph deep learning interatomic potential for the periodic table,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T23:15:24.865585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde588f7-83ed-497c-ab76-48640552173a · outbound

This paper cites Atomistic line graph neural network for improved materials property predictions. npj computational materials, 7 (1): 185,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Atomistic line graph neural network for improved materials property predictions. npj computational materials, 7 (1): 185,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.333653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8bebab16-aef7-4400-8e5e-027d567c8cd8 · outbound

This paper cites Graph networks as a universal machine learning framework for molecules and crystals,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Graph networks as a universal machine learning framework for molecules and crystals,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.319374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 33a16f76-c6de-4f0f-a1f6-869f2ce06c39 · outbound

This paper cites Gptff: A high-accuracy out-of-the- box universal ai force field for arbitrary inorganic materials,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Gptff: A high-accuracy out-of-the- box universal ai force field for arbitrary inorganic materials,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.307162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 10f6940b-b2bc-4854-b4e6-a9b0f9465dbd · outbound

This paper cites A survey on compiler autotuning using machine learning,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs A survey on compiler autotuning using machine learning,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.293580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation adf0298f-9aad-40f3-9ede-76ffe8b71023 · outbound

This paper cites and y. chen. 2018. tvm: An automated end-to-end optimizing compiler for deep learning,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs and y. chen. 2018. tvm: An automated end-to-end optimizing compiler for deep learning,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.278756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 381da33b-5758-44ce-b380-1d99639e1f33 · outbound

This paper cites Cdnet: A real-time and robust crosswalk detection network on jetson nano based on yolov5,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Cdnet: A real-time and robust crosswalk detection network on jetson nano based on yolov5,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.264172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 28c157a6-5376-4f83-9b18-6182fc45f32c · outbound

This paper cites Ansor: Generating {High-Performance} tensor programs for deep learning,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Ansor: Generating {High-Performance} tensor programs for deep learning,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.248890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4b8698df-43ab-4610-bd81-3649f8b92484 · outbound

This paper cites Operator Fusion in XLA: Analysis and Evaluation.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Operator Fusion in XLA: Analysis and Evaluation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T23:15:24.900162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f35ac9-abaf-4c49-a302-3b9138c865d4 · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Pytorch: An imperative style, high-performance deep learning library,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.232667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7945c91e-e94d-4453-8a1f-45bedaf84fcf · outbound

This paper cites Degree-Quant: Quantization-Aware Training for Graph Neural Networks.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Degree-Quant: Quantization-Aware Training for Graph Neural Networks

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-10T23:15:25.085369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 783540da-91cb-4539-b035-d33d7adcff2b · outbound

This paper cites Qgtc: accelerating quantized graph neural networks via gpu tensor core,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Qgtc: accelerating quantized graph neural networks via gpu tensor core,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.218385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0c4d5a18-7918-4ea4-94f1-ffa4dea6fab5 · outbound

This paper cites Vq-gnn: A universal framework to scale up graph neural networks using vector quantization,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Vq-gnn: A universal framework to scale up graph neural networks using vector quantization,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.202220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5c05c234-6d7f-46d7-8dfa-21169d39f7c0 · outbound

This paper cites Sgquant: Squeezing the last bit on graph neural networks with specialized quantization,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Sgquant: Squeezing the last bit on graph neural networks with specialized quantization,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.188077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0490c001-9141-4dd4-93dc-c941e7e489c3 · outbound

This paper cites Rlekf: an optimizer for deep potential with ab initio accuracy,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Rlekf: an optimizer for deep potential with ab initio accuracy,

Reference 36

Resolution: malformed identifier; no resolver link, observed 2026-08-10T23:15:24.925411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97deb40b-fe9c-476e-a195-4104c26b5b9e · outbound

This paper cites Neural network force field training based on reor- ganized layer-wised extended kalman filter,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Neural network force field training based on reor- ganized layer-wised extended kalman filter,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.171484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0cd44058-2757-403e-87f5-8ec01dc1a11c · outbound

This paper cites The mlip package: moment tensor potentials with mpi and active learning,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs The mlip package: moment tensor potentials with mpi and active learning,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.155729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d89560a6-7d27-40d9-9942-86b67fb0ed49 · outbound

This paper cites Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:15:25.141784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b7315a1e-1327-4c59-8f0a-da25803494f2 · outbound

This paper cites Training one deepmd model in minutes: a step towards online learning,.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Training one deepmd model in minutes: a step towards online learning,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T23:15:24.945850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503e9179-91bb-4c3a-8017-f7f343f72fb5 · outbound

This paper cites Available: https://dx.doi.org/10.1088/2632-2153/abc9fe.

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs Available: https://dx.doi.org/10.1088/2632-2153/abc9fe

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-10T23:15:24.937526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 77f69f3e-07c3-44ef-819b-0549eac65394 · inbound

Facet: highly efficient E(3)-equivariant networks for interatomic potentials cites this paper.

Facet: highly efficient E(3)-equivariant networks for interatomic potentials FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-08-15T16:13:41.301697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.