Spaces:

timchen0618
/

browsecomp-plus-viz

Running

App Files Files Community

browsecomp-plus-viz / backend /data

326 MB

Ctrl+K

Ctrl+K

3 contributors

History: 12 commits

Tim Chen

Update trajectories_corpus from full corpus-v3 bcp run (n=830)

8d1618f 19 days ago

responses_judges.unified.jsonl

3.6 MB
xet

Add closed-book judge verdicts (sourced from full A/B sweep) 29 days ago
structures.jsonl

9.69 MB
xet

Add Structures tab to BrowseComp-Plus viewer about 1 month ago
structures_v1.jsonl

14 MB
xet

Add 'Structures v1' tab (parallel structure-generator run, fuchsia accent) about 1 month ago
structures_v2.jsonl

10.1 MB
xet

Add Structures v2 tab (parallel v2 generation run) about 1 month ago
test_with_chunks.unified.jsonl

102 MB
xet

Add Raw ⟷ Unified view toggle about 1 month ago
test_with_structures.unified.jsonl

19.1 MB
xet

Add Eval Structures v0 tab from unified eval bundle 29 days ago
trajectories.jsonl

61.3 MB
xet

Add LLM judge verdict pill to trajectory viewer 26 days ago
trajectories_corpus.jsonl

106 MB
xet

Update trajectories_corpus from full corpus-v3 bcp run (n=830) 19 days ago