Jixin Audrey Zheng

auragreen's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in harborframework/parity-experiments 21 days ago

Add DiscoverPhysics partial GLM parity evidence

#270 opened 21 days ago by

auragreen

New activity in harborframework/parity-experiments 6 months ago

Add parity experiments for paperbench

#249 opened 6 months ago by

auragreen

updated a dataset 8 months ago

auragreen/harbor-datasets

Updated Jan 6 • 609

New activity in harborframework/harbor-datasets 8 months ago

paperbench: restore rubric.json paragraph in instruction.md, fix f-string escaping

1

#53 opened 8 months ago by

auragreen

paperbench: add addendum.md + blacklist.txt to agent Docker image, expand instruction.md

1

#52 opened 8 months ago by

auragreen

paperbench: fix agent-accessible resources to match upstream PaperBench design

#54 opened 8 months ago by

auragreen

paperbench: fix Dockerfiles and task.toml for remaining 19 tasks

#51 opened 8 months ago by

auragreen

paperbench: fix Dockerfiles and task.toml for parity testing

#50 opened 8 months ago by

auragreen

New activity in harborframework/harbor-datasets 10 months ago

Merged stray gitattributes into one top-level file

1

#47 opened 10 months ago by

auragreen

refs/pr/46

#46 opened 10 months ago by

auragreen

refs/pr/43

#43 opened 10 months ago by

auragreen

Paperbench directory layout cleanup

1

#41 opened 10 months ago by

auragreen

New activity in auragreen/harbor-datasets 10 months ago

paperbench-fix-layout-and-missing

#1 opened 10 months ago by

auragreen

New activity in harborframework/harbor-datasets 10 months ago

paperbench: sync refactor changes (task layout + verifier/test harness)

#40 opened 10 months ago by

auragreen

paperbench: sync local dataset changes on verifier runtime harness

1

#38 opened 10 months ago by

auragreen

Update .gitattributes

2

#37 opened 10 months ago by

auragreen

paperbench: clean resync (delete existing tree first)

1

#36 opened 10 months ago by

auragreen

cleanup: remove accidentally uploaded local-path subtree (Users/...)

#35 opened 10 months ago by

auragreen

paperbench: add harbor.download.include_paths to task.toml for shared paper assets

3

#34 opened 10 months ago by

auragreen

paperbench: provider-agnostic judge env + o3-mini default (o-series reasoning high)

1

#33 opened 11 months ago by

auragreen