add links

.gitignore

@@ -0,0 +1,164 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#  nuclear option because steven uses PyCharm.
+.idea/
+
+# VSCode
+.vscode/

app.py

@@ -58,15 +58,31 @@ def select_columns(df, columns):
 
 demo = gr.Blocks(css=custom_css)
 with demo:
-    with gr.Row():
+    with gr.Column():
         gr.Markdown(
             """<div style="text-align: center;"><h1> 🏎️RACE Leaderboard</h1></div>\
             <br>\
-            <p>Based on the 🏎️RACE benchmark, we demonstrated the ability of different LLMs to generate code that is <b><i>correct</i></b> and <b><i>meets the requirements of real-world development scenarios</i></b>.</p>
-            <p>More details about how to evalute the LLM are available in the <a href="https://github.com/jszheng21/RACE">🏎️RACE GitHub repository</a>.</p>
 """,
             elem_classes="markdown-text",
         )
+        
+        gr.Markdown(
+            """
+            Based on the 🏎️RACE benchmark, we demonstrated the ability of different LLMs to generate code that is **_correct_** and **_meets the requirements of real-world development scenarios_**.
+            
+            More details about how to evalute the LLM are available in the [🏎️RACE GitHub repository](https://github.com/jszheng21/RACE). For a complete description of RACE benchmark and related experimental analysis, please refer to the paper: [**Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models**](https://arxiv.org/abs/2407.11470). [![](https://img.shields.io/badge/arXiv-2407.11470-b31b1b.svg)](https://arxiv.org/abs/2407.11470)
+""",
+            elem_classes="markdown-text",
+        )
+    
+#         gr.Markdown(
+#             """<div style="text-align: center;"><h1> 🏎️RACE Leaderboard</h1></div>\
+#             <br>\
+#             <p>Based on the 🏎️RACE benchmark, we demonstrated the ability of different LLMs to generate code that is <b><i>correct</i></b> and <b><i>meets the requirements of real-world development scenarios</i></b>.</p>
+#             <p>More details about how to evalute the LLM are available in the <a href="https://github.com/jszheng21/RACE">🏎️RACE GitHub repository</a>. For a complete description of RACE benchmark and related experimental analysis, please refer to the paper: Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models</p>
+# """,
+#             elem_classes="markdown-text",
+#         )
 
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
         with gr.Column():

text_content.py

@@ -24,17 +24,20 @@ Additionally, factors involving execution-based evaluation are conducted in a vi
 
 # Contact
 If you have any questions, feel free to reach out to us at [[email protected]](mailto:[email protected]).
-
-# Citation Information
-```bibtex
-
-```
 """
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
 
 CITATION_BUTTON_TEXT = r"""
-
+@misc{zheng2024race,
+      title={Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models}, 
+      author={Jiasheng Zheng and Boxi Cao and Zhengzhao Ma and Ruotong Pan and Hongyu Lin and Yaojie Lu and Xianpei Han and Le Sun},
+      year={2024},
+      eprint={2407.11470},
+      archivePrefix={arXiv},
+      primaryClass={cs.SE},
+      url={https://arxiv.org/abs/2407.11470}, 
+}
 """
 
 ACKNOWLEDGEMENT_TEXT = """