> For the complete documentation index, see [llms.txt](https://docs.everesteer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.everesteer.ai/scoring/ncorr.md).

# NCORR

Your contribution beyond the average of the core features.

NCORR rewards predictions that **carry signal beyond a frozen core feature set**. It is computed exactly like [AIMC](/scoring/aimc.md), with the equal-weight average of the core features standing in for the benchmark. A model that simply tracks the core features contributes nothing.

The core set is frozen and train-selected. The same reference is used wherever NCORR is reported: the Himalayas round score, the validation-diagnostics panel, and training-time checks. A displayed NCORR and a paid NCORR never come from different features.

{% stepper %}
{% step %}

### Average the core features

Per exped, take the equal-weight average of the core features for each id. A feature missing for an id is left out of that id's average; an id with every core feature missing drops out.
{% endstep %}

{% step %}

### Rank-gaussianize

Your predictions and that average, per exped. The same rank transform CORR uses.
{% endstep %}

{% step %}

### Orthogonalize

Remove the component of your predictions that lies along the average. A scalar projection, not a regression on many features.
{% endstep %}

{% step %}

### Covariance

Take the covariance of that residual with the centred target. Too few overlapping ids means NCORR is 0.0 for that exped.
{% endstep %}

{% step %}

### When the average lost

If the average's own covariance with the target is negative for that exped, NCORR is 0 for that exped, exactly as AIMC is when the benchmark lost.
{% endstep %}
{% endstepper %}

{% hint style="info" %}
NCORR is **null** when none of the core features are present on the scored frame. The term is skipped rather than recomputed over a different feature space. On event boards, a null NCORR means that entry has no round score, not a zero.
{% endhint %}

{% hint style="warning" %}
The `everestapi[scoring]` extra ships its own re-implementation of the scoring kernels, which may lag the server. Official NCORR is server-side. Use the toolkit for relative comparisons.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.everesteer.ai/scoring/ncorr.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.