2233admin / llm-as-a-verifier
jsonmain115de30733.1K linessynced 20h ago
Code health
10.0out of 10Excellent
This codebase scores 10.0 out of 10 on defect risk, which we rate excellent. It also scores maintainability 10.0 and static performance risk 10.0 out of 10. The three are scored separately and never blended into one number.
- Lines of code
- 733.1K
Recent activity
All commitsNeeds attention
12 open- medium severity. ProposedDeepSeek reasoning budget must cover both reasoning trace and score tagsAuto-proposed decision awaiting review
- medium severity. ProposedFine-grained verifier reward via expectation over score-token distributionAuto-proposed decision awaiting review
- medium severity. Knowledge silollm_verifier/__init__.py100% single-owner concentration
- medium severity. Knowledge silollm_verifier/__main__.py100% single-owner concentration
- medium severity. Knowledge silollm_verifier/benchmarks.py100% single-owner concentration
Composition
Open the graphjson 98%python 1%markdown 1%toml 0%
Explore this codebase
- Docs27 pages across 4 modules
- ChatAsk this codebase a question and get an answer with its sources
- Files912 files with per-file docs, health and history
- ArchitectureDependency graph, layers, and 2 entry points
- Code healthPer-file scores, 83 open findings, coverage and refactoring targets
- Knowledge graphEntities, communities, and the paths between them
- Change couplingFiles that keep changing together, mined from commit history
- CommitsChange-risk ranked history with agent provenance
- ContributorsBus factor, per-file maintainers, and the human/agent split
- StatsSize class, origin, lifetime churn, rhythm and records
- CostsWhat indexing this snapshot cost, by model and by run