DOGFOOD – Autonomous Hackathon Evaluation & Scoring Platform

说明与用途

DOGFOOD – 一款自动化平台，消除评委偏见，平衡评审，支持离线评分。

问题

Hackathon judging suffers from anchoring bias, judge variance, uneven review distribution, and offline failures.

结果

Judging bias reduced, review distribution balanced, and offline resilience achieved.

工作流

• Deploy Docker appliance via docker compose up --build
• Judges log in to /dashboard/judge and receive blind queue
• Submit scores through /api/v1/judge/scores
• Organizer monitors progress at /dashboard/organizer
• Scores are calibrated with Empirical Bayes and displayed at /results
• Export CSV via /api/export.csv

证据

DOGFOOD was built to solve these systemic problems once and for all. It is an autonomous, zero‑trust, single‑port offline appliance running on port 8080

来源

Empirical Bayes shrinkage formula: μ̂_i = (n_i · x̄_i + k · μ_0) / (n_i + k)

来源