Arioron Labs

Research.

Applied research with a bias toward constraint. Weights, datasets and evaluation code are published so the claims can be checked.

From the newsroom

Introducing the new VexAI: an assistant with its own computer, rebuilt from the ground up 14 Oct Introducing the new Vex ID: one account for everything Arioron, rebuilt 11 Oct Introducing the new VexAPI: build apps, talk to agents, and ship AI to production 05 Oct

All news

ARL-2025-009 Jul 2026

OncoDetect Titan: robustness over benchmark fit in lung cancer detection

A multi-model ensemble for lung cancer detection, trained explicitly on degraded and inconsistent scan data. We argue that robustness to real hospital conditions matters more than benchmark position, and report sensitivity on an external test set.

Medical Imaging Weights available

Results ARL-2025-009

Sensitivity, external set Recall on held-out data

100.0%

Ensemble members Independently trained networks

6.0

All publications

All Language Models Medical Imaging

No publications under this topic yet.

Five companies, one engineering standard.

Research.

OncoDetect Titan: robustness over benchmark fit in lung cancer detection

All publications