# Conference: {Title}

> **Quick Conference Mode** — Minimal preset for testing whether your problem benefits from the conference format.
> ~12 total iterations + review overhead. Fast enough to validate the approach before committing to a full run.

## Goal
{Describe what the conference should achieve. Be specific and measurable.}

## Mode
metric

## Success Metric
- **Metric:** {e.g., "accuracy", "execution_time_seconds", "score"}
- **Target:** {e.g., "> 95%", "< 50ms", "> 8/10"}
- **Direction:** {maximize | minimize}

## Researchers
- **Count:** 2
- **Iterations per round:** 3
- **Max rounds:** 2

## Search Space
- **Allowed changes:** {What researchers CAN modify}
- **Forbidden changes:** {What researchers CANNOT modify — e.g., test data, eval scripts}

## Search Space Partitioning
- **Strategy:** free

## Constraints
- **Max total iterations:** 12
- **Time budget:** 30m
- **Researcher timeout:** 15m

## Current Approach
{Describe the baseline. What exists now?}

## Shared Knowledge
<!-- Auto-populated after each round with validated findings -->

## Context & References
{Background material — papers, docs, URLs, code files}

---

## Conference Log
<!-- Auto-maintained by Conference Chair. Do not edit manually. -->
| Round | Researcher | Best Metric | Key Finding | Status |
|-------|-----------|-------------|-------------|--------|
