fix: relabel qwen3.5:9b 2026-04-07 as BrowseComp (was mislabeled SimpleQA)#12
Merged
LearningCircuit merged 1 commit intomainfrom Apr 9, 2026
Merged
fix: relabel qwen3.5:9b 2026-04-07 as BrowseComp (was mislabeled SimpleQA)#12LearningCircuit merged 1 commit intomainfrom
LearningCircuit merged 1 commit intomainfrom
Conversation
…ed SimpleQA) The LDR YAML exporter hard-coded dataset as "SimpleQA". This run was actually xbench_deepsearch. Move to results/xbench-deepsearch/ and fix the dataset field. LDR exporter fix: LearningCircuit/local-deep-research#3442
c9df301 to
00aef39
Compare
LearningCircuit
added a commit
that referenced
this pull request
Apr 10, 2026
peter-evans/create-pull-request restores the workspace to the base branch HEAD after creating its PR, reverting the freshly rebuilt leaderboards/CONTRIBUTORS files in the working tree. Running HF sync after this step uploaded the OLD main state, causing the HF dataset to silently lag behind the actual repo state. Symptom: after PR #12 (xbench relabel) merged, the publish workflow reported "Sync CSVs + README to Hugging Face: success" with the HF API responding "No files have been modified since last commit" — the workspace files at sync time matched HF because peter-evans had already restored them to main HEAD (which still had the pre-rebuild SimpleQA mislabel). Fix: move HF sync BEFORE the create-pull-request step so it operates on the freshly rebuilt files.
1 task
LearningCircuit
added a commit
that referenced
this pull request
Apr 10, 2026
peter-evans/create-pull-request restores the workspace to the base branch HEAD after creating its PR, reverting the freshly rebuilt leaderboards/CONTRIBUTORS files in the working tree. Running HF sync after this step uploaded the OLD main state, causing the HF dataset to silently lag behind the actual repo state. Symptom: after PR #12 (xbench relabel) merged, the publish workflow reported "Sync CSVs + README to Hugging Face: success" with the HF API responding "No files have been modified since last commit" — the workspace files at sync time matched HF because peter-evans had already restored them to main HEAD (which still had the pre-rebuild SimpleQA mislabel). Fix: move HF sync BEFORE the create-pull-request step so it operates on the freshly rebuilt files.
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.
Summary
The qwen3.5:9b 2026-04-07 submission (merged as PR #10) was actually a BrowseComp run, not SimpleQA. The LDR exporter had a second bug: `dataset: SimpleQA` was hard-coded regardless of the actual benchmark.
This PR:
The exporter fix is in LearningCircuit/local-deep-research#3442.