# Test-Time Compute ROI Audit

## Description
Calculates cost-per-accuracy return curves for Best-of-N sampling, search depth scaling, and verifier reranking vs base model upgrading.

## Category
`reasoning`

## Tags
`test-time-compute`, `best-of-n`, `verifier`, `reasoning`, `roi`

## When to Use
Determine whether scaling test-time search delivers higher accuracy per dollar than migrating to a larger frontier model.

## Operational Limitations
Evaluates candidate generation and verifier pricing. Assumes calibrated reward model ranking.

## Verification Script
Run the deterministic verification checker:
```bash
python3 scripts/check.py examples/synthetic.json
```
Exit codes:
- `0`: Check passed and thresholds satisfied.
- `1`: Threshold breach or operational violation detected.
- `2`: Schema error or invalid usage.