Thorsu/evidence-bound-agent-evals download history
Thorsu/evidence-bound-agent-evals is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 455 times (455 in the last 7 days), and 455 times in total. It ranks #35,679 among datasets by monthly downloads.
Evidence-Bound Agent Evals A community protocol for evidence-bound AI evaluation. Instead of only model-to-score results, each contribution can bind: claim -> execution evidence -> verifier -> provenance -> integrity What this is This project treats evidence itself as a