AI Science Tracker
EN

A machine-learning potential predicts reconstruction at a twisted SrTiO₃ interface

Affiliation not stated in the reviewed arXiv metadata · 2 Nov 2026 · materials

Discovery

A machine-learning potential predicts reconstruction at a twisted SrTiO₃ interface

Source check: Source checked. Not independent scientific confirmation.

Finding: A density-functional-theory-trained machine-learning potential predicted near-interface reconstruction at a twisted SrTiO₃ interface, which the study compared with atomic-resolution microscopy. The structural result concerns the prepared interface; electronic and switching outcomes are not attributed to the AI prediction.

Technology: Density-functional-theory-trained machine-learning interatomic potential

Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
A learned interatomic potential predicted atomic reconstruction for comparison with experimental microscopy.
Test and result
The predicted near-interface reconstruction was compared with the observed atomic structure in microscopy.
Limitation / still unknown
The result concerns the studied twisted SrTiO₃ interface; electronic and switching outcomes are not attributed to the AI prediction.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://arxiv.org/abs/2611.02464v1 · https://arxiv.org/pdf/2611.02464v1

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse materials discoveries.