Every strip deserves a referee

The problem we kept running into

Fencing has a referee shortage everywhere below the elite level. At club night, two lights go on, both fencers turn to whoever's nearby, and the point gets settled by seniority, volume, or a shrug. The sport's most interesting rule — right-of-way — is also its most argued about, and most fencers go years without reliable feedback on it.

What we built

Verdict is a computer-vision system that makes the call from a single phone camera. It tracks both fencers and both blades frame by frame, reads the scoring lights directly from the video, and judges the phrase the way a referee does — then explains its reasoning, so every touch teaches something.

Built on real expertise, not scraped guesses

Behind the model is one of the largest expert-labeled fencing datasets ever assembled: 23,500+ touches from real competition, each reviewed by a team of experienced fencers and referees who label the winner and the action. That annotation operation — dozens of contributors, referee-validated labels, continuous quality review — is the real moat, and it grows every week.

Our promise: published numbers

An AI that makes officiating calls owes its users honesty about how often it's right. We publish our accuracy openly — per action type, including the calls we're still bad at — and the model says "not sure" instead of bluffing. When the numbers improve, we update the page; we never publish a projection as a result.

Where we are

Verdict is in development, starting with sabre — the fastest weapon and the hardest right-of-way problem. Early access opens to the waitlist first, free tier included. If you run a club and want to be part of early testing, we'd especially love to hear from you at [email protected].