kulibinai/cadevolve

--- license: apache-2.0 pretty_name: CADEvolve dataset_type: synthetic --- # CADEvolve: Creating Realistic CAD via Program Evolution **CADEvolve** is a synthetic dataset for **CAD reverse engineering** built around **executable CadQuery programs**. It is produced by the CADEvolve pipeline, which evolves a small set of primitives into **8k complex parametric generators**, and then expands them into a large corpus of CAD programs (≈1.3M scripts) exercising a broad CadQuery operation set. - Paper: [arXiv:2602.16317](https://arxiv.org/abs/2602.16317) - Code: [GitHub](https://github.com/zhemdi/CADEvolve) ## Repository structure This dataset repo contains **three top-level folders**: ### `CADEvolve-G/` - `parametric_generators.json`: the library of **parametric generator programs** (the evolved generator set). - `embeddings/`: precomputed embeddings for retrieval / indexing (optional utility). ### `CADEvolve-P/` Three subfolders with **`.py` CAD programs**: - `ABC-P/` - `CADEvolve-P-core/` - `ShapeNet-P/` ### `CADEvolve-C/` Three subfolders with **`.py` CAD programs**: - `ABC-C/` - `CADEvolve-C-core/` - `ShapeNet-C/` ## Citation ```bibtex @article{elistratov2026cadevolve, title={CADEvolve: Creating Realistic CAD via Program Evolution}, author={Elistratov, Maksim and Barannikov, Marina and Ivanov, Gregory and Khrulkov, Valentin and Konushin, Anton and Kuznetsov, Andrey and Zhemchuzhnikov, Dmitrii}, journal={arXiv preprint arXiv:2602.16317}, year={2026} }