# evaluation

Comparing two runs and judging one: the comparability rules that decide whether a comparison is meaningful, and the metric policies that turn numbers into a verdict.

Every name on this page is imported from `helia_profiler`.

**API tier:** `experimental`

Generated from the `src/helia_profiler` tree `fe269596788d6ab1604cf433559e96b5f48c1d13`.

[Machine-readable model](https://ambiqai.github.io/helia-profiler/reference/api/helia_profiler/evaluation.json)

Preferred candidate direction for one metric.

**API tier:** `experimental`

Verdict when a selected metric is unavailable.

**API tier:** `experimental`

`dataclass`

One machine-readable compatibility decision.

**API tier:** `experimental`

`dataclass`

Authoritative validity and structured issues for one completed run.

**API tier:** `experimental`

Regression policy outcome.

**API tier:** `experimental`

`dataclass`

Whether run-level and per-layer deltas may be computed.

**API tier:** `experimental`

Per-region used/free rows are gated on the link family (#206).

Whether one metric group's rows may be computed (#206): no
METRIC_BLOCKING issue carrying that group's tag.

`dataclass`

Tolerance and availability policy for one named comparison metric.

**API tier:** `experimental`

`classmethod`

`dataclass`

Open v1 profile selecting deterministic metric regression policies.

**API tier:** `experimental`

`classmethod`

`classmethod`

`dataclass`

Full comparison between two profile runs.

**API tier:** `experimental`

Compare identity, validity, topology, and intentional run dimensions.

**API tier:** `experimental`

`dataclass`

Verdict and evidence for one selected metric.

**API tier:** `experimental`

Evaluate captured results without mutating pipeline state.

**API tier:** `experimental`

`dataclass`

Deterministic verdict for one result pair and profile.

**API tier:** `experimental`

Evaluate existing metric deltas against one versioned profile.

**API tier:** `experimental`

Effect of one comparability issue on comparison output.

Defined here so the comparability registry can bind severity to code
without importing from ``evaluation``; ``evaluation.comparability``
re-exports it, which remains the canonical public import path.

**API tier:** `experimental`

---

Machine-readable: [`evaluation.json`](https://ambiqai.github.io/helia-profiler/reference/api/helia_profiler/evaluation.json) · [`evaluation.md`](https://ambiqai.github.io/helia-profiler/reference/api/helia_profiler/evaluation.md), complete and lossless.