Metraipolis › archive › dc_bf89315ddfac

Foundation Neural-Network Quantum States for Molecular Potential Energy Surfaces in Second Quantization — arXiv:2609.37733

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37733
License (as archived): CC0-1.0
Archived: 2026-10-07T17:33:05.791Z
SHA-256 of the archived text: 586f515f31ed47f31d0e160cd7a18fe23b9f10959987d1e7b24093a4f32c43d5
Stable URL of this page: https://metraipolis.com/documento/dc_bf89315ddfac

How to cite

Foundation Neural-Network Quantum States for Molecular Potential Energy Surfaces in Second Quantization — arXiv:2609.37733 — arXiv (en), https://arxiv.org/abs/2609.37733 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf89315ddfac (Metraipolis archive dc_bf89315ddfac, sha256 586f515f31ed47f31d0e160cd7a18fe23b9f10959987d1e7b24093a4f32c43d5)

BibTeX

@misc{dcbf89315ddfac,
  title = {Foundation Neural-Network Quantum States for Molecular Potential Energy Surfaces in Second Quantization — arXiv:2609.37733},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37733},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf89315ddfac; sha256 586f515f31ed47f31d0e160cd7a18fe23b9f10959987d1e7b24093a4f32c43d5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37733. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Second-quantized neural-network quantum states have achieved accurate molecular energies, but extending them across molecular geometries requires a shared representation of the geometry-dependent wavefunction coefficients. We introduce geometry-conditioned foundation neural-network quantum states for molecular electronic structure in second quantization. A single autoregressive model learns a family of ground states from sparse anchor geometries and provides wavefunctions at untrained geometries without further optimization. Orbital alignment matches orbital identities and transports their phases, establishing an aligned orbital basis across geometries. Frozen energies reach chemical accuracy at every untrained query geometry for N$_2$, CO, and H$_4$. On additional molecular paths, the energy-trained wavefunctions yield dipoles, quadrupoles, and natural occupations without property labels. Across three paired N$_2$ training seeds, orbital alignment lowers the mean absolute energy error over all untrained query geometries from 34-37 mHa to 0.049-0.085 mHa. At approximately 1 mHa mean absolute error, frozen evaluation reduces the per-geometry cost by $986\times$ relative to independent optimization, yielding an estimated $25.8\times$ end-to-end GPU-cost reduction on a 161-point N$_2$ grid.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Chemical Physics (physics.chem-ph) ; Machine Learning (cs.LG); Quantum Physics (quant-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.37733 — 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 2026-10-07T16:59:48.576Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).