Update src/tasks_content.py

src/tasks_content.py

@@ -20,6 +20,10 @@ TASKS_DESCRIPTIONS = {
         * `API Recall`: share of library-specific API calls used in the reference program that appear in the generated code,  
 
         For further details on the dataset and the baselines from the 🏟️ Long Code Arena team, refer to the `library_based_code_generation` directory in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines).
+        
+        If you have any questions or requests concerning this dataset, please contact us at lca@jetbrains.com.
+        
+        **Terms of use**. As this dataset is collected from GitHub, researchers may use it for research purposes only if any publications resulting from that research are open access (see [GitHub Acceptable Use Policies](https://docs.github.com/en/site-policy/acceptable-use-policies/github-acceptable-use-policies#7-information-usage-restrictions)). 
         """,
 
     "ci_builds_repair": """# CI builds repair\n
@@ -37,6 +41,10 @@ TASKS_DESCRIPTIONS = {
         * `oracle: files, lines` – ground truth diffs are used to select files and code blocks that should be corrected to fix the issue;
 
         For further details on the dataset and the baselines from the 🏟️ Long Code Arena team, refer to the `ci-builds-repair` directory in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines).
+        
+        If you have any questions or requests concerning this dataset, please contact us at lca@jetbrains.com.
+        
+        **Terms of use**. As this dataset is collected from GitHub, researchers may use it for research purposes only if any publications resulting from that research are open access (see [GitHub Acceptable Use Policies](https://docs.github.com/en/site-policy/acceptable-use-policies/github-acceptable-use-policies#7-information-usage-restrictions)). 
         """,
 
     "project_code_completion": """# Project-level code completion\n
@@ -60,6 +68,10 @@ TASKS_DESCRIPTIONS = {
         * *random* – lines that don't fit any of the previous categories.
 
         For further details on the dataset and the baselines from the 🏟️ Long Code Arena team, refer to the `project_level_code_completion` directory in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines).
+        
+        If you have any questions or requests concerning this dataset, please contact us at lca@jetbrains.com.
+        
+        **Terms of use**. As this dataset is collected from GitHub, researchers may use it for research purposes only if any publications resulting from that research are open access (see [GitHub Acceptable Use Policies](https://docs.github.com/en/site-policy/acceptable-use-policies/github-acceptable-use-policies#7-information-usage-restrictions)). 
         """,
 
     "commit_message_generation": """# Commit message generation\n
@@ -84,7 +96,10 @@ TASKS_DESCRIPTIONS = {
         We used information retrieval metrics such as `R@k`, `P@k`, `F1-score`, and `MAP` for evaluation, taking `k` equal to 1 and 2.
 
         For further details on the dataset and the baselines from the 🏟️ Long Code Arena team, refer to the `bug_localization` directory in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines).
+
+        If you have any questions or requests concerning this dataset, please contact us at lca@jetbrains.com.
         
+        **Terms of use**. As this dataset is collected from GitHub, researchers may use it for research purposes only if any publications resulting from that research are open access (see [GitHub Acceptable Use Policies](https://docs.github.com/en/site-policy/acceptable-use-policies/github-acceptable-use-policies#7-information-usage-restrictions)). 
     """,
 
     "module_summarization": """# Module summarization\n
@@ -95,6 +110,10 @@ TASKS_DESCRIPTIONS = {
         * `CompScore`: the new metric based on LLM as an assessor proposed for this task. Our approach involves feeding the LLM with relevant code and two versions of documentation: the ground truth and the model-generated text. More details on how it is calculated can be found in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines/blob/main/module_summarization/README.md).
 
         For further details on the dataset and the baselines from the 🏟️ Long Code Arena team, refer to the `module_summarization` directory in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines/blob/main/module_summarization/).
+        
+        If you have any questions or requests concerning this dataset, please contact us at lca@jetbrains.com.
+        
+        **Terms of use**. As this dataset is collected from GitHub, researchers may use it for research purposes only if any publications resulting from that research are open access (see [GitHub Acceptable Use Policies](https://docs.github.com/en/site-policy/acceptable-use-policies/github-acceptable-use-policies#7-information-usage-restrictions)). 
         """,
 }