Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: ScoreBasedAmbiguityResolution to avoid very high score. #4052

Merged
merged 6 commits into from
Jan 29, 2025

Conversation

Ragansu
Copy link
Contributor

@Ragansu Ragansu commented Jan 28, 2025

This PR aims to fix the issue of very high scores (~1e20, ~1e40) when the number of hits per detector exceeds the maximum number of hits allowed.

--- END COMMIT MESSAGE ---

The issue happened because (nHits - maxHits became negative) and this negative number was assigned to an unsigned integer. (the wrap-around causing large values)

Thanks @Corentin-Allaire

Summary by CodeRabbit

  • Bug Fixes
    • Updated track scoring calculation to improve ambiguity resolution logic
    • Refined hit-based scoring mechanism to potentially enhance track selection accuracy

Copy link

coderabbitai bot commented Jan 28, 2025

Walkthrough

In the realm of particle tracking, a subtle yet significant modification has emerged within the ScoreBasedAmbiguityResolution method. The ambiguity scoring algorithm has been refined, altering how track hits are evaluated relative to a detector's maximum hit capacity. The change inverts the previous scoring calculation, potentially reshaping how track candidates are assessed and selected.

Changes

File Change Summary
Core/include/Acts/AmbiguityResolution/ScoreBasedAmbiguityResolution.ipp Modified scoring calculation from score * (detector.maxHits - nHits + 1) to score * (nHits - detector.maxHits + 1)

Poem

Hits and scores, a dance they weave 🌟
Numbers twist, algorithms perceive
One sign flipped, a cosmic jest
Track selection put to the test 🚀
In physics' realm, changes breathe

Hmm, subtle is the code's new way 🧘‍♂️


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 5fb6edc and 1d0fd7e.

📒 Files selected for processing (1)
  • Core/include/Acts/AmbiguityResolution/ScoreBasedAmbiguityResolution.ipp (1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (10)
  • GitHub Check: CI Bridge / build_exatrkx_cpu
  • GitHub Check: CI Bridge / clang_tidy
  • GitHub Check: unused_files
  • GitHub Check: linux_ubuntu_extra (ubuntu2204, 20, clang++)
  • GitHub Check: missing_includes
  • GitHub Check: macos
  • GitHub Check: linux_ubuntu_extra (ubuntu2204, 20, g++)
  • GitHub Check: linux_ubuntu
  • GitHub Check: build_debug
  • GitHub Check: docs
🔇 Additional comments (1)
Core/include/Acts/AmbiguityResolution/ScoreBasedAmbiguityResolution.ipp (1)

339-339: Overflows prevented, negative wrap-around avoided, hmmm.

Correct the logic, you did, to avoid negative wrap-around in unsigned arithmetic, yes. Verify thoroughly, we must, that extremely large values shall not overflow. Careful with the new formula, be! Good indeed this fix is.

✅ Verification successful

Safe from overflow and wrap-around, this formula is. Hmmmm.

The multiplication of score by (nHits - detector.maxHits + 1) creates no risk of overflow or negative wrap-around. When nHits exceeds detector.maxHits, the score increases linearly with additional hits - a desirable behavior that rewards longer tracks while maintaining reasonable magnitudes. For ML-based scoring, the initial score is bounded between 0 and 1, making the final result directly proportional to the number of extra hits.

🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Searching for usage of 'ambiguityScore' or 'score' to ensure
# negative or overly large values, it does not produce.
rg "ambiguityScore|score" -A 5

Length of output: 68234


Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Generate unit testing code for this file.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai generate unit testing code for this file.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and generate unit testing code.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@github-actions github-actions bot added the Component - Core Affects the Core module label Jan 28, 2025
@github-actions github-actions bot added this to the next milestone Jan 28, 2025
Copy link
Contributor

@Corentin-Allaire Corentin-Allaire left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good !

Copy link

github-actions bot commented Jan 28, 2025

📊: Physics performance monitoring for 6de41d3

Full contents

physmon summary

@kodiakhq kodiakhq bot merged commit e61fa2d into acts-project:main Jan 29, 2025
42 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants