Repository navigation
1.2.0: issue localisation (SWE-bench Lite holdout Acc@5 0.587 → 0.750 vs BM25), where_to_look, 8× faster cold index - #135
Merged
Conversation
…harness - get_context_packet adds `where_to_look` for a pasted issue/bug report (60+ words): the localisation list `packet --json` already returns. Instructions mention it. - Version 1.2.0; changelog entry. - SWE harness: an existing worktree is moved to the next commit in place (django worktree re-creation per instance made runs IO-bound, ~10x slower), and shards split by a stable hash of the instance id (shards that start while another run writes the same files overlapped). - Research log: rejected graph-neighbour vote; session-17 handoff. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…5 0.301/0.507/0.587/0.721 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Release branch for 1.2.0.
SWE-bench Lite test, run once (tuned only on the SWE-bench dev split), file-level Acc@1/3/5/10, 276 strict holdout issues:
CPU only, no LLM; p50 2.8 s per issue including a cold index.
get_context_packetaddswhere_to_lookfor pasted issues / bug reports (smoke-tested over stdio)Engine changes already merged: #131, #132, #133, #134. Twelve benchmark sets unchanged (#134).
🤖 Generated with Claude Code