chore: benchmark corpus, baseline results, and implementation requirements#109
Open
stephenc222 wants to merge 1 commit into
Open
chore: benchmark corpus, baseline results, and implementation requirements#109stephenc222 wants to merge 1 commit into
stephenc222 wants to merge 1 commit into
Conversation
REQ-001: history depth tier annotation on ranked output REQ-002: convention_bug_fix_count as 10th ranker feature REQ-003: ranker explanation layer (✦ phrases, --explain flag) REQ-004: public benchmark corpus design with pinned SHAs and versioned results All four backed by findings from hotspots-research. REQ-001–003 are ready to implement. REQ-004 benchmark infrastructure is partially complete. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
stephenc222
force-pushed
the
chore/benchmarks-and-requirements
branch
from
23e1ced to
5ed4dd5
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
benchmarks/— a reproducible public benchmark that validates hotspots' bug-prediction accuracy across 7 well-known, deliberately hard reposdocs/requirements/with four fully-specified implementation specs (REQ-001 through REQ-004)STATUS.mdas the working tracker for open implementation workBenchmark baseline (v1.25.3, ARS formula, no trained ranker)
Corpus: 7 repos · features pinned to pre-2024 SHAs · labels from 2024 bug-fix commits only · fixed label window prevents score drift over time.
Requirements docs ready to implement
HistoryDepthtier annotation on ranked outputconvention_bug_fix_countas 10th ranker feature--explainphrase layer (✦ lines on CRITICAL/HIGH)REQ-002 triggers a benchmark re-run when it ships.
Test plan
benchmarks/label.pyandbenchmarks/score.pyrun without error on a repo with a bare clone availablebenchmarks/versions/v1.25.3.jsonis valid JSON (python3 -m json.tool benchmarks/versions/v1.25.3.json)benchmarks/RESULTS.mdrenders correctly on GitHubSTATUS.mdrenders correctly on GitHub🤖 Generated with Claude Code