Spaces:

Harsh-9209
/

silent-failure-detector

Sleeping

App Files Files Community

silent-failure-detector

636 kB

Ctrl+K

1 contributor

History: 19 commits

Harsh-9209

fix(phase2): return score-only grader payloads to avoid out-of-range numeric fields

1bd6abf 3 months ago

data
feat: add seed dataset and update inference logic to support hallucination evaluation 4 months ago
server
Add files to pass OpenEnv multi-mode validation 3 months ago
src
fix(phase2): return score-only grader payloads to avoid out-of-range numeric fields 3 months ago
tests
fix(eval): mathematically bound all precision/recall metrics via laplace smoothing to naturally yield strict (0, 1) scores without artificial clipping 3 months ago
.gitignore

199 Bytes
Apply strict .gitignore and remove untracked artifacts 4 months ago
Dockerfile

233 Bytes
fix(docker): switch base image registry to public ecr to bypass docker hub rate limits 3 months ago
README.md

6.86 kB
feat: implement FastAPI server, Streamlit dashboard, and unit tests for SilentFailureDetector environment 3 months ago
dashboard.py

1.37 kB
feat: implement FastAPI server, Streamlit dashboard, and unit tests for SilentFailureDetector environment 3 months ago
inference.py

9.18 kB
fix(phase2): return score-only grader payloads to avoid out-of-range numeric fields 3 months ago
main.py

1.97 kB
fix(phase2): return score-only grader payloads to avoid out-of-range numeric fields 3 months ago
openenv.yaml

707 Bytes
feat: implement FastAPI server, Streamlit dashboard, and unit tests for SilentFailureDetector environment 3 months ago
pyproject.toml

499 Bytes
Add files to pass OpenEnv multi-mode validation 3 months ago
requirements.txt

116 Bytes
Include OpenEnv MVP implementation and inference baseline fixes 4 months ago
uv.lock

574 kB
Add files to pass OpenEnv multi-mode validation 3 months ago