How we know

Every number we publish comes from a script over exported data, and the plan for that script was written before anyone took the test.

The plan

Analysis plan tag: prereg-v1 (not yet tagged). The plan names the outcome, the test, the exclusions and the sample size before the first participant.

What a participant does

  1. Reads the consent text and ticks two boxes.
  2. Picks the healthier of two creeks (a warm-up, not scored).
  3. Is assigned by the server to see the lesson first or the test first.
  4. Answers Yes, No or Can't tell on sixteen photos, four per feature.
  5. Sees their score per feature, and may keep it with a random token.

How numbers reach the README

Scripts in evals/ write files in results/. A check in CI compares every number in the README with those files. Nobody types a number by hand.

AI on the same test

Vision models take the same sixteen photos. A model may only raise a question about a feature it passed, and the volunteer always answers first.