> 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/aimc.md).

# AIMC

Covariance after orthogonalizing against the designated benchmark.

AIMC rewards predictions that **diverge from the designated benchmark while still being correct**. A model that simply reproduces the benchmark contributes nothing, however high its CORR.

The reference is the fixed designated benchmark in every lane.

{% stepper %}
{% step %}

### Rank-gaussianize

Your predictions and the designated benchmark, per exped.
{% endstep %}

{% step %}

### Orthogonalize

Remove the component of your predictions that lies along the benchmark. 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 AIMC is 0.0 for that exped.
{% endstep %}

{% step %}

### When the benchmark lost

If the benchmark's own covariance with the target is negative for that exped, AIMC is 0 for that exped.
{% endstep %}
{% endstepper %}

## What the reference is

| Surface              | Reference                                                                          |
| -------------------- | ---------------------------------------------------------------------------------- |
| Himalayas, resolved  | The designated benchmark. A round without a benchmark reference refuses to settle. |
| Himalayas, partial   | The same designated benchmark series.                                              |
| Events / diagnostics | The event's benchmark predictions.                                                 |

## Why copying the benchmark scores nothing

The orthogonalization step removes the component of your predictions that lies along the benchmark. If your predictions are identical to the benchmark, the residual is zero everywhere, and the covariance with the target is also zero. Only signal that differs from the benchmark and is still correct earns an AIMC score.

{% hint style="warning" %}
AIMC, CORR and NCORR are added with equal weight before the round score's arctan. Call `explain_scoring` for the live formula rather than assuming it.
{% 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/aimc.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.