Pinned Loading
Repositories
Showing 10 of 42 repositories
- ContractBench Public
ContractBench: evaluating observation contract failures (validity + integrity) in LLM agents. 33 harbor-runnable API-contract tasks with deterministic programmatic evaluation.
- ContractBench-inspect Public
Inspect AI eval for ContractBench — 33 observation-contract tasks (validity + integrity). Register-ready for inspect_evals.
-
- oss-fuzz-lisa Public Forked from google/oss-fuzz
OSS-Fuzz - continuous fuzzing for open source software.