Add reference to DeepSeekMath in accuracy_reward docstring

[qgallouedec]

What does this PR do?

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a GitHub issue? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

---

Note

Low Risk
Low risk: documentation-only change that adds an academic reference and does not modify runtime behavior.

Overview
Adds a citation to the DeepSeekMath paper in the accuracy_reward docstring to document the origin of the reward/verification approach, without changing any logic.

^{Written by Cursor Bugbot for commit dca45db. This will update automatically on new commits. Configure here.}

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.