docs(cfm): fix compute_conditional_flow docstring formula (t -> xt in numerator)

[MukundaKatta]

Summary

`TargetConditionalFlowMatcher.compute_conditional_flow` (`torchcfm/conditional_flow_matching.py`, lines 370-394) documents the target conditional flow as:

```
ut(x1|x0) = (x1 - (1 - sigma) t)/(1 - (1 - sigma)t)
```

but the implementation returns:

```python
return (x1 - (1 - self.sigma) * xt) / (1 - (1 - self.sigma) * t)
```

which matches Eq.(21) of Lipman et al., ICLR 2023 — the numerator uses the position `xt`, not the time scalar `t`. Updated the summary (line 372) and the Returns description (line 386) so both say:

```
ut(x1|x0) = (x1 - (1 - sigma) xt)/(1 - (1 - sigma)t)
```

Closes #175

Testing

Docstring-only change; no runtime paths touched.

Summary by Sourcery

Documentation:

• Fix the compute_conditional_flow docstring formula so the numerator uses xt instead of t, aligning documentation with the implementation and Eq.(21) of Lipman et al., ICLR 2023.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

This PR corrects the docstring formula for TargetConditionalFlowMatcher.compute_conditional_flow so that it matches the actual implementation and the referenced paper, replacing an incorrect use of t in the numerator with xt in both the summary line and the Returns section.

File-Level Changes

Change	Details	Files
Align the compute_conditional_flow docstring formula with the implemented equation and Lipman et al. Eq.(21).	Update the docstring one-line summary to use xt instead of t in the conditional vector field numerator. Update the Returns description to use xt instead of t in the conditional vector field numerator, keeping the denominator unchanged.	torchcfm/conditional_flow_matching.py

Assessment against linked issues

Issue	Objective	Addressed	Explanation
#175	Correct the compute_conditional_flow docstring so that the conditional vector field formula uses the position xt (x) in the numerator instead of the time scalar t, matching Eq.(21) and the implementation.	✅

Possibly linked issues

• Typo in comment: wrong formula in compute_conditional_flow docstring (line ~372) #175: The PR exactly fixes the docstring formula typo in compute_conditional_flow described in the issue (t → xt).

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've reviewed your changes and they look great!

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[atong01]

Thanks for the PR!