Pilot datasetOne prompt · one trial · 33 routes · not the official Core rankingRead the limits

Blind pairwise evaluation

Watch first.
Reveal second.

Judge complete motion, not provider reputation. Votes are deduplicated, weighted conservatively, and disclosed with uncertainty.

Preparing a matched comparison…

01Watch both

Scrub or replay before deciding.

02Pick honestly

Tie and both-miss are valid answers.

03Then reveal

Names appear only after a qualified vote.