Franziska Weindel

FWeindel's activity

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

New activity in FWeindel/task-defect-ground-truth 4 days ago

Point task records to packages without later git history and without reviewed hacks

#9 opened 4 days ago by

FWeindel

Add SWE task packages without later git history and move two reviewed hacks out of their packages

1

#8 opened 4 days ago by

FWeindel

New activity in FWeindel/task-defect-ground-truth 5 days ago

Point SWE task records to the packages that keep the SWE-bench setup commit

#7 opened 5 days ago by

FWeindel

Add SWE task packages that keep the SWE-bench setup commit

#6 opened 5 days ago by

FWeindel

Point SWE task records to packages that keep the SWE-bench setup commit

#5 opened 5 days ago by

FWeindel

Add SWE task packages that keep the SWE-bench image setup commit

#4 opened 5 days ago by

FWeindel

Exclude django__django-10097 from the shared PASS set

1

#3 opened 5 days ago by

FWeindel

New activity in FWeindel/validated-tasks 8 days ago

Add calibforge_v4 unfiltered judge annotations

#32 opened 10 days ago by

llincke

New activity in FWeindel/task-defect-ground-truth 11 days ago

Relabel five SWE tasks after a demonstrated git history exploit

#2 opened 11 days ago by

FWeindel

New activity in FWeindel/validated-tasks 15 days ago

FineEnvs v3: 515 newly solved tasks and all 1,998 Qwen/Qwen3.8-27B attempts

#31 opened 16 days ago by

FWeindel

New activity in FWeindel/validated-tasks 22 days ago

Simplify MultiSWE release layout

1

#29 opened 22 days ago by

FWeindel

Add MultiSWE cached images (1/42)

#28 opened 22 days ago by

FWeindel

Add NL2Bash v3: 104 newly solved tasks, 1042 kept

#27 opened 22 days ago by

FWeindel

New activity in FWeindel/validated-tasks 23 days ago

FineEnvs v1: 5,000 kept tasks

#26 opened 23 days ago by

FWeindel

Prepare NL2Bash v2 with 938 tasks solved by Coder pass@4

#25 opened 23 days ago by

FWeindel

New activity in FWeindel/validated-tasks 25 days ago

Add MiMo Code: 2,509 validated tasks

#24 opened 25 days ago by

FWeindel

New activity in FWeindel/validated-tasks 26 days ago

nl2bash_v1: validation run 2026-10-17-nl2bash_v1-b0c10dccb2cd

1

#23 opened 26 days ago by

FWeindel

New activity in FWeindel/validated-tasks 27 days ago

Add completed SETA pass16 recovery evidence

1

#21 opened 27 days ago by

FWeindel

Add TermiGen cached images and v2 teacher trajectories

#20 opened 28 days ago by

llincke

New activity in FWeindel/validated-tasks 28 days ago

Endless Terminals: 2,145 retained tasks, 347 archived; phases 3–5

#19 opened 28 days ago by

llincke