An AI-native discovery engine

Findings the published baselines assumed, measured.

Assay runs a closed loop. It takes an old or underused dataset, asks one falsifiable question, isolates one variable, and measures how much of a claimed result is really there. Each turn is published as a citable, downloadable paper. Negative results count.

1 discovery published. Have a dataset you want assayed? Request one.

No. 008 published

A zero-pixel clock recovers most of the surgical-phase signal on Cholec80

A predictor that sees zero pixels and knows only where a frame sits in time reaches 70.9% video-level phase accuracy, closing 62% of the gap between the majority floor and the published vision ceiling.

Surgical video Cholec80 2026-06-21

70.9% phase accuracy with zero pixels (matched splits)