> 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/events-and-hackathons/how-an-event-runs.md).

# How an event runs

{% stepper %}
{% step %}

### Fit offline

Fit your model on the labeled training split.
{% endstep %}

{% step %}

### Predict on the open round

Download the rows the currently open round serves (`download_dataset(split='live')`) and submit. That is the scored split.
{% endstep %}

{% step %}

### Ignore validation for the result

`validation` is the day-0 practice board that runs before round 1: ranked, but not one of the scored rounds and never counted toward the event result. It ships blind and server-scored just like `live`.
{% endstep %}

{% step %}

### Accumulate

An event normally runs as a sequence of **sealed rounds** on a shared clock. Only the round that is currently open is being scored. Each round has its own board. Per-round scores accumulate into the **cumulative standings**, which is the result that decides the event.
{% endstep %}
{% endstepper %}

{% hint style="info" %}
Whether a given event also scores a separate held-out final window is reported by `get_diagnostics_leaderboard(window='final')`. That is the authority on it. Do not assume either way.
{% endhint %}

## Ranking

Boards rank on the round score: a weighted blend of CORR20, AIMC and NCORR, clipped per round, on the same weights the Himalayas tournament pays on. All three terms are measured out-of-sample against the realised `target_everest_20`; in-sample fit is not rewarded.

Call `explain_scoring` for the live numbers and do not assume which term dominates. A board falls back to ranking on CORR20 only when nothing on it is scored yet. `rank_metric` on the leaderboard response reports what a given board was actually ordered by.


---

# 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/events-and-hackathons/how-an-event-runs.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.