A benchmarking experiment finds low rediscovery rates for three models on six Mythos-linked bug tasks, with only six target matches across 54 attempts under controlled prompting.
OSS-Fuzz: Google’s continuous fuzzing service for open source software
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking Mythos-Linked Bug Rediscovery
A benchmarking experiment finds low rediscovery rates for three models on six Mythos-linked bug tasks, with only six target matches across 54 attempts under controlled prompting.