> 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/partial-scores-and-resolution.md).

# Partial scores and resolution

Running scores while the target window fills, then the resolved score.

Your submitted predictions do not change after the round closes. What changes is the target they are scored against. Partial and resolved use the same target construction, evaluated at different realised horizons.

```mermaid
flowchart LR
    Close[Round closes] --> Partial[Partial scores]
    Partial --> Resolved[Resolved score]
    Resolved --> Settle[Settlement]
```

{% columns %}
{% column %}

### Partial

Each later trading session scores your unchanged predictions against the primary target's construction realised over the sessions elapsed so far, up to the full horizon. That running target is binned exactly like the resolved one.

Partial AIMC uses the same designated benchmark series. Partial CORR is against that session's realised target.
{% endcolumn %}

{% column %}

### Resolved

Once the round is in resolved status, scoring uses the mature, binned primary target. That is the round's result. Later partial days do not keep revising it.
{% endcolumn %}
{% endcolumns %}

Several rounds can be in this window at once, each on its own exped. That overlapping book is why a given day can update more than one round.

## When partials appear and when a round resolves

The first partial score appears after the first trading session following the round's data date. The scoring window officially opens 3 trading sessions after the data date. The resolved score arrives when the primary target's full horizon has matured, which is 23 trading sessions after the data date (the 20-day horizon plus a 2-session lag plus the close day). Holidays move these offsets; read the round's own dates from the API.

{% hint style="info" %}
Partials use the same round-score formula as resolution, so a partial payout and the resolved payout for a round are the same quantity at different horizons.
{% endhint %}

## Where to read partial scores

Two endpoints expose the running scores:

* **`GET /api/v1/rounds/{round}/daily-progression`**: the benchmark-average walk for a round. The MCP tool `get_round_daily_progression` returns the same data.
* **`GET /api/v1/rounds/{round}/models/{model}/daily-progression`**: one of your own models' day-by-day trajectory (your own models only). The MCP tool `get_model_daily_progression` returns the same data.

Each returns a day-by-day series from the first session after the round. Days with no data are absent, not zero-filled.

## Settlement

A round's scores can be final while its USDC settlement is still pending. Nothing has changed about your payout. You will be notified when settlement completes.


---

# 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/partial-scores-and-resolution.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.