LICENSE
README.md
pyproject.toml
sia/__init__.py
sia/context_manager.py
sia/orchestrator.py
sia/prepare_mlebench_dataset.py
sia/util.py
sia/tasks/__init__.py
sia/tasks/_shared/reference_target_agent.py
sia/tasks/_shared/sample_agent_execution.json
sia/tasks/gpqa/data/private/diamond_questions.json
sia/tasks/gpqa/data/public/diamond_questions.json
sia/tasks/gpqa/data/public/evaluate.py
sia/tasks/gpqa/data/public/task.md
sia/tasks/gpqa/reference/SAMPLE_TASK_DESCRIPTIONS.md
sia/tasks/gpqa/reference/reference_target_agent.py
sia/tasks/lawbench/data/private/test.csv
sia/tasks/lawbench/data/public/classes.json
sia/tasks/lawbench/data/public/evaluate.py
sia/tasks/lawbench/data/public/sample_submission.csv
sia/tasks/lawbench/data/public/task.md
sia/tasks/lawbench/data/public/test.csv
sia/tasks/lawbench/data/training_data/task.md
sia/tasks/lawbench/data/training_data/test.csv
sia/tasks/lawbench/data/training_data/train.csv
sia/tasks/lawbench/reference/SAMPLE_TASK_DESCRIPTIONS.md
sia/tasks/lawbench/reference/reference_target_agent.py
sia/tasks/longcot-chess/data/private/answers.json
sia/tasks/longcot-chess/data/public/chess_hard.json
sia/tasks/longcot-chess/data/public/evaluate.py
sia/tasks/longcot-chess/data/public/task.md
sia/tasks/longcot-chess/reference/SAMPLE_TASK_DESCRIPTIONS.md
sia/tasks/longcot-chess/reference/reference_target_agent.py
sia/tasks/spaceship-titanic/data/private/test.csv
sia/tasks/spaceship-titanic/data/public/sample_submission.csv
sia/tasks/spaceship-titanic/data/public/task.md
sia/tasks/spaceship-titanic/data/public/test.csv
sia/tasks/spaceship-titanic/data/public/train.csv
sia/tasks/spaceship-titanic/reference/SAMPLE_TASK_DESCRIPTIONS.md
sia/tasks/spaceship-titanic/reference/reference_target_agent.py
sia_agent.egg-info/PKG-INFO
sia_agent.egg-info/SOURCES.txt
sia_agent.egg-info/dependency_links.txt
sia_agent.egg-info/entry_points.txt
sia_agent.egg-info/requires.txt
sia_agent.egg-info/top_level.txt
tests/test_context_manager.py
tests/test_orchestrator_helpers.py
tests/test_task_structure.py