Two scenarios
Calibration Cup: 4 judges × 30 projects (seed 20260928), project i skips judge i mod 4, one constant-3.0 judge, two thinly reviewed projects, one duplicate Solar Kiosk. Grand Jury: the same idea at fixture scale, 30 judges × 40 projects, 118 rows (seed 20260929).
Both write their assignment plan to the audit trail as assignment.generate with seed, rule and loads — then both verdicts land FRAGILE on camera.
python demo-5min/seed_judging_demo.py
node demo-5min/make.mjs # narrate + record + muxWhat the videos show
e2e-demo-5min.mp4 (3:56): landing, Calibration Cup tour, duplicate side-by-side, live participant submit, audit trail, progress 23/22/21/23, live judge scoring, CSV download, then terminal proofs — 403s, FRAGILE diff, run.py 7/7 PASS. Narrated twins use offline TTS (Microsoft Zira) from demo-5min/narration/.
Run it yourself
Every post maps to a real route or file in this repo. Start with the gallery, then the docs.
Keep reading
View allOct 3, 2026 · Engineering
Run the whole platform with one command: setup guide (main branch)
Clone main, docker compose up, seed fixtures, test accounts, and the 7/7 acceptance checker — everything to go from zero to judging in minutes.
Oct 3, 2026 · Company
Build the platform that will judge you: how we built DOGFOOD 2026
FastAPI + Next.js + Postgres with backend-enforced judge isolation, z-score calibration and one-command Docker — our Write-Up Quest build log.
Sep 28, 2026 · Engineering
Fair ranking is not an average: z-scores, Bradley-Terry and Borda
Raw averages reward lucky judge draws. How per-judge calibration plus two extra ranking views produce a ROBUST/FRAGILE verdict organizers can defend.