Upload README.md with huggingface_hub

README.md

@@ -62,9 +62,16 @@ quirks: `animal-welfare`, `contextual-optimism`, `hardcode-test-cases`, `self-pr
 
 ## Evaluation
 
-The evaluation kit that reproduces our behaviour / belief / capability / μ-decisiveness numbers on
-these organisms — vendored task code, prompt and scenario data, judge rubrics, and a single runner —
-is published separately; see the `evalkit` link in the repo card discussion or contact the authors.
+**[`djroytburg/auditbench-graft-evalkit`](https://huggingface.co/datasets/djroytburg/auditbench-graft-evalkit)**
+reproduces our behaviour / belief / capability / μ-decisiveness numbers on these organisms: the exact
+scenario and prefill data, the judge rubric, the frozen belief-probe weights, vendored task code, and
+one runner that takes an arm name and an eval name.
+
+```bash
+python run_eval.py --eval elicit --arm s2-graft-kto --quirk co
+```
+
+Its README carries the serving contract and the failure modes that silently produce wrong numbers.
 
 ## Intended use, limitations, safety