Update src/tasks_content.py

src/tasks_content.py

@@ -27,7 +27,9 @@ TASKS_DESCRIPTIONS = {
         Our CI builds repair benchmark 🤗 [JetBrains-Research/lca-ci-builds-repair](https://huggingface.co/datasets/JetBrains-Research/lca-ci-builds-repair) 
         includes 77 manually curated and assessed data points coming from 32 Python repositories, which are used to make a model fix a failed build.
 
-        We use the `Pass@1` metric for CI repair.
+        The benchmark clones the repo to the local folder. The baseline model fixes the issue according to logs and the local repo state,
+        and then the benchmark pushes the repo to GitGub and requests the result of the GitHub CI.
+        We use the `Pass@1` rate metric for CI repair.
         Models can be evaluated in three types of tasks:
         * `full` – **no** ground truth diffs are used for model evaluation;
         * `oracle: files` – ground truth diffs are used to select files that should be corrected to fix the issue;