gradia-reward-loop rudycelekli · PARTIAL
Oracle-witnessed reward-hacking experiments and a replay-verified paired GRPO diagnostic.
github.com/rudycelekli/gradia-reward-loop · ★ 0 · Forks 0 · Size 18.7 MB
SUMMARY
Technologies 10
Scored 7
Observed 7
Practices 6
Evidence 11
Skips 3
COVERAGE
Analyzed 73 files · 33 commits · 0 API calls
TECHNOLOGIES & DEPTH
JSON LANGUAGE Depth 70
11 files · PRODUCTION
TOML LANGUAGE Depth 70
1 files · PRODUCTION
Markdown LANGUAGE Depth 70
11 files · PRODUCTION
YAML LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
28 files · PRODUCTION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 74
14 files · PRODUCTION
Ruff QUALITY Depth —
0 files · config only
mypy QUALITY Depth —
0 files · config only
pytest TESTING Depth —
0 files · config only
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-09-01
Last commit 2026-09-03
Active months 1
Commits 33