The authors conclude that, for neural quantum states to simulate realistic models, the main open problem is generalization rather than expressibility.

The paper

The paper's details are OpenAlex's; the citation count is OpenAlex's, 14 Oct 2026. The line on the paper is machine-written, as noted under Why it matters.

Why it matters

Written by Claude (claude-sonnet-5-5) on 14 Oct 2026 from the paper's abstract (as arXiv publishes it) and its OpenAlex record. Machine-written context to help a reader: it is not evidence, it moves no number, and it may be wrong. The quoted sentence is the claim; where it stands is computed from the record. If it misreads the paper, tell the stewards.

The story so far

1. 1

   What the authors did

   They trained neural networks to approximate the ground states of several moderately sized frustrated-magnet Hamiltonians, using the wavefunction on a small subset of the Hilbert space basis as the training data.

   Machine-written from the paper's abstract, as noted under Why it matters.

2. 2

   What they found

   • Generalization quality, meaning the ability to learn from few samples and approximate the target state on the rest of the space, drops abruptly as frustration increases.
   • Learning the sign structure of the wavefunction is considerably more difficult than learning its amplitudes.
   • The main issue to address for realistic models is generalization rather than expressibility.

   Machine-written from the paper's abstract, as noted under Why it matters.

3. 3

   What has been checked on Ecdysis

   Exuvia registered it on 14 October 2026. Its credence, the record's estimate that it holds, is 0.55 on a scale from 0 (refuted) to 1 (established): where it started, as every claim from the literature does. Only independent evidence moves it.

What would check it

How sure is the record?

Share this finding

Ready-made posts, written from the record. You post them yourself, from your own account; nothing is ever posted for anyone.

Click a post's text to select all of it. Both posts give the claim's standing on the record, and the longer one says what the checks show and what they do not; the wording changes when the record does. The longer post quotes the paper first, then gives the machine-written headline, marked as such; edit it as you like. To cite the claim, see Cite this claim.

What would prove it wrong

Refuted if, for a set of realistic quantum many‑body models, the best achievable variational energy using neural quantum states is limited by the expressive capacity of the network architecture (e.g., no improvement when increasing model depth or width) while generalisation from a fixed training dataset does not degrade performance beyond statistical noise.

The test as Exuvia registered it on 14 Oct 2026, written from the paper's words. A conceptual claim's test names its refuter in words: it is checked by argument.

The wider literature

Other claims from the same paper

• uncheckedIn this study, neural networks trained on a few samples of a magnet's ground state generalise much worse once frustration in the model is increased.“We notice that generalization quality, i.e. the ability to learn from a limited number of samples and correctly approximate the target state on the rest of the space, drops abruptly when frustration…”
• uncheckedWe also show that learning the sign structure is considerably more difficult than learning amplitudes.

Headlines are machine-written from the paper's abstract, or from the quote and the paper's title where no abstract is open; each claim's own words are quoted beneath its headline.