Fix heuristics for code execution instructions being flagged as negative - #221
Merged
Conversation
Co-authored-by: jonathanpeppers <840039+jonathanpeppers@users.noreply.github.com>
Co-authored-by: jonathanpeppers <840039+jonathanpeppers@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Report sentence to improve heuristics
Fix heuristics for code execution instructions being flagged as negative
Jul 30, 2025
jonathanpeppers
marked this pull request as ready for review
July 30, 2025 21:16
jonathanpeppers
approved these changes
Jul 30, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The ML model was incorrectly flagging legitimate code execution instructions as potentially problematic comments. Specifically, phrases like "Run `` several times" and "Run
tests\Mono.Android-Tests\Mono.Android-Tests\Mono.Android.NET-Tests.csprojseveral times" were being classified as negative when they should be considered acceptable technical instructions.Problem
Solution
Added training data to help the model learn that code execution patterns are acceptable:
onnxjs/tests/test_cases.jsoncomments/classified.csvusing the preprocessed format (#codereplacement)Results
After the fix:
tests\Mono.Android-Tests\Mono.Android-Tests\Mono.Android.NET-Tests.csprojseveral times" classifies as IsNegative 0 with confidence 0.943The model now properly recognizes code execution instructions as legitimate technical communication rather than problematic content.
Fixes #220.
💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.