Spaces:

AashishPatnaik
/

AusRegBench

Running

App Files Files Community

1.11 MB

Ctrl+K

Ctrl+K

1 contributor

History: 25 commits

ashe0042

Add benchmark results for dashboard deployment

56004c5 2 months ago

.vscode
Auto-activate .venv in Cursor terminal 2 months ago
dashboard
Add dashboard-only requirements.txt to fix Streamlit Cloud deployment 2 months ago
data
Download APRA prudential standards CPS 220/230/234 as PDFs 2 months ago
queries
Gold set complete: 120 hand-verified queries across 5 strata and 5 sources 2 months ago
results
Add benchmark results for dashboard deployment 2 months ago
scripts
Benchmark run complete: 595/600 evaluations, grounded cuts misstatements 56% vs naive 2 months ago
src
Benchmark run complete: 595/600 evaluations, grounded cuts misstatements 56% vs naive 2 months ago
.gitignore

114 Bytes
Ignore raw benchmark results from git 2 months ago
CLAUDE.md

9.81 kB
Initial scaffold: gitignore, env, CLAUDE.md 2 months ago
requirements.txt

257 Bytes
Streamlit dashboard: professional dark theme, correct bar charts, example failures 2 months ago