Spaces:

AashishPatnaik
/

AusRegBench

Running

App Files Files Community

AusRegBench / src

46.5 kB

Ctrl+K

Ctrl+K

1 contributor

History: 14 commits

ashe0042

Benchmark run complete: 595/600 evaluations, grounded cuts misstatements 56% vs naive

1a8d5dc 2 months ago

configs
LangSmith tracing wired into all five configs and eval harness 2 months ago
__init__.py

0 Bytes
Clause-aware chunker: paragraph ID preservation, header fix, SCHEDULE tagging, APRA artifact filter 2 months ago
db.py

1.18 kB
Benchmark run complete: 595/600 evaluations, grounded cuts misstatements 56% vs naive 2 months ago
embed.py

2.51 kB
Embed all corpus chunks with text-embedding-3-large (11613 chunks, /bin/zsh.23) 2 months ago
eval.py

1.78 kB
LangSmith tracing wired into all five configs and eval harness 2 months ago
ingest.py

7.97 kB
Clause-aware chunker: paragraph ID preservation, header fix, SCHEDULE tagging, APRA artifact filter 2 months ago
judge.py

8.78 kB
Phase 3 complete: two-layer judge with deterministic citation checker, LLM entailment judge, Cohen's kappa — smoke test passed 2 months ago
retrieval.py

4.38 kB
Retrieval layer: dense search + BM25 + RRF combiner (smoke test verified) 2 months ago