Spaces:

timchen0618
/

browsecomp-plus-viz

Running

App Files Files Community

browsecomp-plus-viz / scripts

16.7 kB

Ctrl+K

Ctrl+K

3 contributors

History: 7 commits

timchen0618's picture

Add LLM judge verdict pill to trajectory viewer

e5e16fd verified 23 days ago

build_eval_structures.py

3.13 kB
Add Eval Structures v0 tab from unified eval bundle 26 days ago
build_responses_judges.py

5.56 kB
Add closed-book judge verdicts (sourced from full A/B sweep) 26 days ago
build_structures.py

3.3 kB
Add Structures v2 tab (parallel v2 generation run) 30 days ago
build_trajectories.py

4.75 kB
Add LLM judge verdict pill to trajectory viewer 23 days ago