Investigate CoDoC approach for some models
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 570
- Forks
- 351
- Avg merge
- 2d 13h
- Merged PRs (30d)
- 65
Description
https://deepmind.google/discover/blog/codoc-developing-reliable-ai-tools-for-healthcare/
For example, it could be interesting in bug component assignment, or in spam detection.
Maybe even test selection: if the model is not sure about a platform for example, it could defer to the developer.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked CoDoC article, then inspect Bugbug's existing model workflows for bug component assignment, spam detection, and test selection. The issue does not name files or tests; done would require a scoped investigation and a documented decision about whether a CoDoC-style approach is viable for one of these models.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100