Metraipolis › archive › dc_77166b9d7686

Diagnosing Latent Energy Decomposition in Machine-Learning Interatomic Potentials via Interacting Quantum Atoms — arXiv:2609.00674

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00674
License (as archived)
CC0-1.0
Archived
2026-10-17T07:21:28.234Z
SHA-256 of the archived text
118dcc97c334510ba877c9175ab96d74c6bc3cbcb0d4edb3045074213d846219
Stable URL of this page
https://metraipolis.com/documento/dc_77166b9d7686

How to cite

Diagnosing Latent Energy Decomposition in Machine-Learning Interatomic Potentials via Interacting Quantum Atoms — arXiv:2609.00674 — arXiv (en), https://arxiv.org/abs/2609.00674 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_77166b9d7686 (Metraipolis archive dc_77166b9d7686, sha256 118dcc97c334510ba877c9175ab96d74c6bc3cbcb0d4edb3045074213d846219)
BibTeX
@misc{dc77166b9d7686,
  title = {Diagnosing Latent Energy Decomposition in Machine-Learning Interatomic Potentials via Interacting Quantum Atoms — arXiv:2609.00674},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00674},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_77166b9d7686; sha256 118dcc97c334510ba877c9175ab96d74c6bc3cbcb0d4edb3045074213d846219},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00674. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Machine-learning interatomic potentials (MLIPs) can reproduce potential energies and forces accurately, but their internal energy allocation is often difficult to interpret. E3D-IQA is introduced as a diagnostic framework connecting the latent edge-energy representation of an Allegro-type MLIP with Interacting Quantum Atoms (IQA) energy decomposition. The Allegro edge-energy path is retained as a latent pair contribution, while a node-energy path is trained against the IQA intra-atomic energy. IQA interatomic energies are not direct training targets; instead, the learned edge energies are evaluated after training against the IQA pair terms. Tests on H/C/N/O organic reaction structures show that intra-atomic supervision is essential: energy and force training alone does not recover an IQA-like one-body/two-body allocation. With intra-atomic supervision, node energies reproduce IQA intra-atomic terms, and latent edge energies show meaningful correspondence with IQA interatomic terms. Residual errors are concentrated in positive or weak pair interactions, exposing internal allocation failures that remain hidden in total-energy and force metrics. Adding structures labeled only with energies and forces improves transfer to larger molecules and reduces decomposition errors. E3D-IQA therefore provides a route for diagnosing and guiding latent scientific representations using partially labeled quantum-chemical datasets.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-02 in physics.comp-ph).
Categorie arXiv: Chemical Physics (physics.chem-ph) ; Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.00674 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:16:49.919Z dalla pagina https://arxiv.org/catchup/physics.comp-ph/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).