> 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/data.md).

# Data

The Atlas dataset: one obfuscated feature matrix, rank-based targets, three splits.

The served dataset is **Atlas**. One obfuscated feature matrix with rank-based targets, split three ways: `train`, `validation` and `live`. Features are cross-sectionally ranked, binned into ten levels and renamed. Raw source data is never exposed through the API or the files.

{% hint style="info" %}
This section describes the **tournament** dataset. An event or hackathon may be served a different one, with a different number of feature bins, a different target panel and a different `id` shape. Those are declared per dataset: call `get_dataset_schema` and read its `feature_encoding` and `target_encoding` blocks, or read the range straight off the values you downloaded, which are the bin codes themselves. See [Events & hackathons](/events-and-hackathons.md).
{% endhint %}

Each row is keyed by `exped` (one as-of day: every row that was knowable on that day, one cross-section) and a row `id`. Row identifiers are obfuscated and unique per row per exped, so a name in one exped never matches a name in another. Join rows on the `id` column of the split you downloaded. Do not hardcode an instrument id.

{% hint style="info" %}
Dataset scale (feature and target counts, split boundaries) is published in `eiq_metadata.json`, which ships with every download. Row and instrument counts come from the files themselves. These pages describe the shape and the mechanism, not the numbers.
{% endhint %}

## In this section

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Splits &#x26; obfuscation</strong></td><td>Train, validation, live: what each holds and how the data is obfuscated.</td><td><a href="/data/splits-and-obfuscation.md">Splits &amp; obfuscation</a></td></tr><tr><td><strong>Datasets</strong></td><td>What you can download, which split tokens exist, and how fresh the files are.</td><td><a href="/data/datasets.md">Datasets</a></td></tr><tr><td><strong>All dataset files</strong></td><td>Every downloadable artifact in the Atlas tree.</td><td><a href="/data/all-dataset-files.md">All dataset files</a></td></tr><tr><td><strong>Feature groups</strong></td><td>How the feature space is named, typed, binned and organised into sets.</td><td><a href="/data/feature-groups.md">Feature groups</a></td></tr><tr><td><strong>Column definitions</strong></td><td>Schema for Atlas. Read the live list from `eiq_features.json`.</td><td><a href="/data/column-definitions.md">Column definitions</a></td></tr><tr><td><strong>Targets</strong></td><td>The primary payout target, the auxiliary targets, and their values.</td><td><a href="/data/targets.md">Targets</a></td></tr><tr><td><strong>Benchmark models</strong></td><td>The designated benchmark and the reference models, and what they are for.</td><td><a href="/data/benchmark-models.md">Benchmark models</a></td></tr></tbody></table>


---

# 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/data.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.