IncidentResponseDetective

Sleeping

App Files Files Community

IncidentResponseDetective

1.46 MB

Ctrl+K

6 contributors

History: 86 commits

90shikhar08

Cursor

docs(notes): task design audit — hard runbook leaks answer, medium underspecified

34d236a 3 months ago

.claude
Add adversial mode,evidence validation,benchmark script 4 months ago
data
feat(splits): immutable train/val/test seed splits v1.0.0 3 months ago
eval
feat(eval): async harness with Groq/Gemini/HF adapters and 5-bias matrix 3 months ago
notes
docs(notes): task design audit — hard runbook leaks answer, medium underspecified 3 months ago
results
feat(eval): async harness with Groq/Gemini/HF adapters and 5-bias matrix 3 months ago
scripts
feat(eval): async harness with Groq/Gemini/HF adapters and 5-bias matrix 3 months ago
server
chore: add gitignore for __pycache__, stop tracking pyc files 3 months ago
.gitattributes

1.62 kB
Add training plot: reward_curve.png 3 months ago
.gitignore

250 Bytes
fix: rewrite .gitignore as UTF-8 (was UTF-16 BOM, patterns silently failing) 3 months ago
.graphify_python

65 Bytes
Add adversial mode,evidence validation,benchmark script 4 months ago
Dockerfile

295 Bytes
Add files via upload 4 months ago
README.md

27 kB
Clarify DAG demo download instructions for HuggingFace Spaces 3 months ago
WRITEUP.md

5.69 kB
Replace WRITEUP.md with finalized version 3 months ago
__init__.py

55 Bytes
Add files via upload 4 months ago
app.py

445 Bytes
Replace root app.py with compatibility wrapper pointing to canonical server.app 3 months ago
before_after.png

25.5 kB
Fix: swap plot filenames - evaluation_by_difficulty.png now shows difficulty breakdown, before_after.png shows aggregate 3 months ago
benchmark.py

5.2 kB
Add adversial mode,evidence validation,benchmark script 4 months ago
benchmark_results.json

2.43 kB
Add adversial mode,evidence validation,benchmark script 4 months ago
bias_types.py

1.52 kB
feat(bias): 5-type bias taxonomy and seeded overlay generators 3 months ago
client.py

1.54 kB
Add files via upload 4 months ago
dag_demo.html

26.6 kB
Add interactive DAG visualization demo for service dependency cascade 3 months ago
environment.py

2 kB
Add compatibility wrapper for root environment.py to support legacy scripts while maintaining OpenEnv compliance 3 months ago
evaluation_by_difficulty.png

23.5 kB
Fix: swap plot filenames - evaluation_by_difficulty.png now shows difficulty breakdown, before_after.png shows aggregate 3 months ago
inference.py

15.7 kB
Fix: Add matplotlib dependency and fix embedded mode crash 3 months ago
loss_curve.png

50.9 kB
xet

Regenerate plots from trainer_state.json (384 steps, TRL log_history) 3 months ago
models.py

1.59 kB
Add files via upload 4 months ago
openenv.yaml

475 Bytes
Polish for submission: experimental tracking detail, loss curve note, env naming, architecture clarity, cross-validation framing 3 months ago
procedural_generator.py

40.5 kB
feat(bias): 5-type bias taxonomy and seeded overlay generators 3 months ago
pyproject.toml

468 Bytes
feat(eval): async harness with Groq/Gemini/HF adapters and 5-bias matrix 3 months ago
regenerate_plots.py

7.15 kB
Regenerate plots from trainer_state.json (384 steps, TRL log_history) 3 months ago
requirements.txt

196 Bytes
feat(eval): async harness with Groq/Gemini/HF adapters and 5-bias matrix 3 months ago
reward_curve.png

124 kB
xet

Add training plot: reward_curve.png 3 months ago
splits.py

4.07 kB
feat(bias): 5-type bias taxonomy and seeded overlay generators 3 months ago
task_definitions.py

19 kB
Resolve all merge conflicts, push Round 2 to HF Space 3 months ago
train.py

13.3 kB
feat: Add --dry-run flag for quick validation 3 months ago
training_log.json

369 Bytes
final: OpenEnv base class inheritance + training log 3 months ago
upload_pngs.py

2.52 kB
Pre-submission cleanup: writeup consolidation, eval script, upload utilities 3 months ago
upload_trainer_state.py

3.46 kB
Security: Replace hardcoded token with environment variable 3 months ago
uv.lock

538 kB
Update uv.lock 4 months ago