code/pyproject.toml

[project]
name = "csd-repro"
version = "0.1.0"
description = "Claim-by-claim reproduction of 'Curated Synthetic Data Doesn't Have to Collapse' (arXiv:2605.07724)"
readme = "README.md"
requires-python = "==3.12.*"
dependencies = [
    "numpy==2.1.3",
    "scipy==1.14.1",
    "sympy==1.13.1",
    "mpmath==1.3.0",
    "pandas==2.2.3",
    "matplotlib==3.9.2",
    "torch==2.5.1",
    "torchvision==0.20.1",
    "transformers==4.46.3",
    "tokenizers==0.20.3",
    "datasets==3.1.0",
    "huggingface-hub==0.26.3",
    "pillow==11.0.0",
]

[tool.uv]
# CPU-only torch. This project is explicitly forbidden from using GPUs.
[[tool.uv.index]]
name = "pytorch-cpu"
url = "https://download.pytorch.org/whl/cpu"
explicit = true

[tool.uv.sources]
torch = [{ index = "pytorch-cpu", marker = "sys_platform == 'linux'" }]
torchvision = [{ index = "pytorch-cpu", marker = "sys_platform == 'linux'" }]

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.build.targets.wheel]
packages = ["repro"]