Strengths3
- Clear and well-documented convention (MurphySig) with empirical validation.
- Functional benchmark harness with CLI for running, scoring, and reporting.
- Includes heuristic scoring for local analysis without API calls.
Benchmarking Project · Python
Natural-language provenance convention for signing human-AI collaborative code. Spec, CLI, and empirical benchmark.
An organisation's project: the project boards rank individual builders, so it is shown here without a rank. Among builders' projects it would sit 31st in NLP & LLMs.
MurphySig is a benchmarking project that evaluates a natural-language provenance convention for human-AI collaborative code. It includes a harness to run experiments across multiple LLM families, measuring effects on AI honesty and code coverage.
Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored
Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.
Read from the project's code at its scored commit.
The owner keeps this project's limitations private.