AI Science Tracker
EN

XCAPE proposes nine previously unmatched crystal structure assignments

Seoul National University; Korea Institute for Advanced Study · 18 Nov 2026 · materials

Discovery

XCAPE proposes nine previously unmatched crystal structure assignments

Source check: Source checked. Not independent scientific confirmation.

Finding: In an arXiv preprint, researchers used XCAPE and the SevenNet-Omni machine learning interatomic potential to revisit existing powder X-ray diffraction patterns. In the subset without matching reference structures, they reported nine plausible atomic arrangements, eight halides and one sulfide, that met diffraction and energy criteria. These are inferred structural assignments from existing measurements and computed energies. The preprint does not establish that the assignments are unique or independently confirmed.

Technology: SevenNet-Omni machine learning interatomic potential (XCAPE)

Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
SevenNet-Omni evaluated energies and relaxed candidate structures during the evolutionary search, supporting selection of candidates for comparison with measured diffraction.
Test and result
Existing powder diffraction patterns were compared with predictions, using an energy criterion to assess plausibility. The nine assignments are the subset reported in Section 2.5.
Limitation / still unknown
Unique assignment and independent experimental confirmation were not established in the reviewed preprint.
Evidence sources and annotation context

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

Evidence sources: https://arxiv.org/html/2611.23760v1

Source checked · editorial details

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

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 20 Nov 2026. Review scope: arXiv v1 abstract, Section 2.5, validation and methods.

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 2/5 · Validation 2/5 · 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.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.