Update src/tasks_content.py

src/tasks_content.py

@@ -24,22 +24,12 @@ TASKS_DESCRIPTIONS = {
 
     "ci_builds_repair": """# CI Builds Repair\n
         
-        Our CI Builds Repair benchmark 🤗 [JetBrains-Research/lca-project-level-code-completion](https://huggingface.co/datasets/JetBrains-Research/lca-project-level-code-completion) includes four datasets:
-        * `small-context`: 144 data points,
-        * `medium-context`: 224 data points,
-        * `large-context`: 270 data points,
-        * `huge-context`: 296 data points.
+        Our CI Builds Repair benchmark 🤗 [JetBrains-Research/lca-ci-builds-repair](https://huggingface.co/datasets/JetBrains-Research/lca-ci-builds-repair) includes 77 data points.
 
-        We use standard Exact Match (EM) metric for one-line code completion.
+        We use Pass@1 metric for CI repair.
         We evaluate Exact Match for different line categories:
-        * *infile* – functions and classes are from the completion file;
-        * *inproject* – functions and files are from the repository snapshot;
-        * *committed* – functions and classes are from the files that were added on the completion file commit;
-        * *common* – functions and classes with common names, e.g., `main`, `get`, etc.;
-        * *non-informative* – short/long lines, import/print lines, or comment lines;
-        * *random* – lines that doesn't fit to any of previous categories.
 
-        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `code_completion` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint (TODO).
+        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `ci-builds-repair` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint.
         """,
 
     "project_code_completion": """# Project-Level Code Completion\n