---
name: undominated-test-time-search-budget-audit
description: "Audits test-time compute search budgets to ensure marginal accuracy gains justify token expenditure. Recomputed fields must match the other inputs. A pass is not a compliance, safety, or price verdict."
license: MIT
metadata:
  author: Undominated.ai
  version: "1.1.0"
---

# Test-time search budget audit

## Description
Audits test-time compute search budgets to ensure marginal accuracy gains justify token expenditure.

## Category
`evaluation`

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

## When to Use
Audit Best-of-N or search-tree reasoning systems to detect diminishing returns in token spending.

## Operational Limitations
Evaluates observed pass@k curves against token budgets; does not generate reasoning trees.

## 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.

## What the checker recomputes

The original threshold checks still apply:

- `marginal_gain_per_k_tokens` must not be < `min_roi_threshold`.

Every other declared field is type-checked. A negative value is rejected except for deltas, drifts, and gains. A type check does not, by itself, prove the measurement.

`population` and `observedAt` are required. The bundled examples are synthetic fixtures, not market measurements.

```bash
python3 scripts/check.py examples/synthetic.json
python3 scripts/check.py examples/contradiction.json
python3 scripts/check.py examples/broken.json
```

Exit 0 is a pass, exit 1 is a review, and exit 2 is invalid input. A pass does not certify a provider, a regulation, a release, or a price.