Rail Vision Ltd. (NASDAQ:RVSN, FSE: C80))) ("Rail Vision" or the "Company"), an early commercialization stage technology company transforming railway safety through advanced AI-integrated sensing systems, announces today, that its majority owned subsidiary Quantum Transportation Ltd. ("Quantum Transportation"), a quantum computing innovator, has successfully delivered a working integration layer that brings a publicly accessible experimental surface-code dataset from Google Quantum AI, into the Quantum Transportation's Quantum Error Correction (QECC) IP (patent pending) transformer pipeline.

In this phase, the team implemented a standardized data adapter to ingest dense binary syndrome measurements from selected experimental configurations, engineered dynamic attention masking that adapts to code distances and layouts, and established an end-to-end training loop capable of processing mixed batches of real experimental shots.

This milestone reduces technical risk by advancing QECC beyond controlled internal data formats and lays the foundation required for scalable training and repeatable benchmarking on a credible external testbed.

Quantum Transportation is developing transformer-based quantum decoder technology for advanced quantum error correction, including cloud-deployed neural decoders. The decoder's IP (patent pending) is licensed from Ramot at Tel Aviv University, with applications in various potential industries and end users.

Quantum Transportation previously announced it has successfully implemented its transformer-based neural decoder on the AWS cloud, marking a significant milestone toward real-world quantum applications within the transportation sector. Building on the recent unveiling of its transformer neural decoder, which outperformed classical quantum error correction (QEC) algorithms in simulations, and the delivery of its first prototype for universal error correction, Quantum Transportation's cloud deployment now provides the scalable infrastructure needed to process complex quantum data efficiently.