MCPcopy Create free account
hub / github.com/davidstutz/confidence-calibrated-adversarial-training

github.com/davidstutz/confidence-calibrated-adversarial-training @main

Chat with this repo
repository ↗ · DeepWiki ↗ · + Follow
1,075 symbols 2,887 edges 104 files 716 documented · 67% updated 6y ago★ 441 open issues

Browse by type

Functions 916 Types & classes 159
What it actually does AI analysis from the code graph — generated when you open this
loading…

Core symbols most depended-on inside this repo

browse all functions →

Shape

Method 741
Function 175
Class 159

Languages

Python100%

Modules by API surface

tests/test_attacks_normal.py73 symbols
common/summary.py63 symbols
common/eval/adversarial_evaluation.py57 symbols
tests/test_eval.py48 symbols
common/torch.py45 symbols
attacks/initializations.py45 symbols
common/eval/corrupted_evaluation.py44 symbols
experiments/config/common.py39 symbols
common/datasets.py39 symbols
common/eval/distal_evaluation.py37 symbols
common/eval/clean_evaluation.py32 symbols
common/paths.py30 symbols

For agents

$ claude mcp add confidence-calibrated-adversarial-training \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact

Ask about this repo answers extend the page