fix: Lower resolved_threshold default from 0.8 to 0.0 for dead code benchmarks#1
Draft
jonathanpopham wants to merge 1 commit intofeat/supermodel-benchmarkfrom
Draft
Conversation
…enchmarks The 80% precision AND recall gate meant every task showed "Resolved: False" for both MCP and baseline agents. No dead code detection approach achieves 80% on both metrics simultaneously — precision is bounded by parser import resolution gaps (see supermodeltools/supermodel-public-api#677). Setting to 0.0 means any task with >0% on both P and R counts as resolved. The threshold is still configurable via config YAML for stricter gating.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
The
resolved_thresholddefaulted to 0.8, meaning a task was only marked "Resolved" if both precision AND recall were ≥ 80%. No dead code detection approach hits this bar. Every task in every run showedResolved: Falsefor both MCP and baseline.Fix
Lower default from 0.8 to 0.0 in both dead code benchmark classes. Any task with non-zero P and R counts as resolved. Still configurable via config YAML.
Context
See supermodeltools/supermodel-public-api#676 for full benchmark analysis.