What Changed at XtalPi

Every material change AI Health Index has tracked at XtalPi: new modules, model and architecture updates, clinical evidence, regulatory status, security certifications, and integration depth. Each entry states what changed, cites its source, and carries our read on what it means for a buyer. The graded assessment of this vendor across all fifteen capability axes sits on its index profile.

Funding rounds, valuations, and awards are not product changes and are not logged here. Acquisitions appear only where there is direct product impact.

Follow this change log by RSS

Free for your reader, newsletter or automation tool. One feed covers the whole index, and every category has its own.

All feeds and terms

Impact

Type

1 entry

Showing changes for XtalPi only.Show the full log

October 2026

X

XtalPi

Oct 12, 2026

MediumVerified

Model / architecture

XtalPi released LCMS2Yield on GitHub under the Apache 2.0 license, with model weights, inference code and datasets. The model predicts UV correction factors from a molecule's structure, so chemists can calculate reaction yields from LC-UV data and an internal standard without a pure reference sample of each product. It pairs a Graph Transformer with a Kolmogorov-Arnold Network, was trained on 22,609 computed and 1,845 measured compounds, and had a 4.74 percent average yield error across 178 reactions.

Our read

Discovery chemistry teams can run and test one of XtalPi's platform models on their own data before engaging its services. The method was published earlier in JACS Au; what is new is the open release of the code and weights.

Related axis: Model and Technology TransparencyVendor announcementView source

What has changed at XtalPi recently?

The most recent change AI Health Index logged at XtalPi is dated Oct 12, 2026. XtalPi released LCMS2Yield on GitHub under the Apache 2.0 license, with model weights, inference code and datasets.