AI-Wiki
Search
Search
Dark mode
Light mode
Explorer
Tag: json-parser
1 item with this tag.
Aug 30, 2026
SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
specbench
reward-hacking
reward-hacking-gap
held-out-tests
long-horizon
benchmark
oversight-surface
os-kernel
json-parser
test-memorization
type/source
kind/paper