{"success":true,"data":{"author":"Cyprien Bone, Keith T. Butler et al. (University College London)","bucketAccessType":"public","bucketName":"c-bone/mattergen_XRD","bucketPrefix":"","category":"Chemistry & Materials","cloudProvider":"huggingface","createdAt":"2026-11-22T01:09:20.766Z","description":"Training data from University College London for CrystaLLM-pi, a property-conditioned transformer that generates crystal structures. It pairs the Alex-MP-20 inorganic crystal structures released with Microsoft's MatterGen (drawn from the Alexandria DFT database and Materials Project MP-20) with up to 20 of their most intense simulated powder X-ray diffraction (XRD) peaks. Peaks were computed with pymatgen's XRDCalculator at the Cu K-alpha wavelength and stored as a condition vector of 2-theta positions followed by intensities, min-max normalized and padded with -100. Each row gives the source database, reduced formula and the structure in CrystaLLM-pi augmented CIF text, with a random 90:10 split of 591,964 training and 65,774 validation rows in Parquet. Use it to train or test models that recover a crystal structure from its diffraction pattern, or for XRD-conditioned materials discovery; load with datasets or pandas. License CC BY 4.0, following the Alexandria and Materials Project source data. Cite Bone et al., Discovery and recovery of crystalline materials with property-conditioned transformers, arXiv:2511.21299.","displayTitle":"MatterGen Alex-MP-20 Crystal Structures with Simulated XRD Peaks for Diffraction-Conditioned Generation (CrystaLLM-pi, UCL)","huggingFaceUrl":"https://huggingface.co/datasets/c-bone/mattergen_XRD","id":"6b66ed04-9d7b-5785-9a9e-b517b4c61ea0","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/c-bone/mattergen_XRD","objectCountEstimate":5,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2511.21299","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"c-bone/mattergen_XRD\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"c-bone/mattergen_XRD\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=c-bone, license:cc-by-4.0, size_categories:100K<n<1M, format:parquet, downloads=80"],"format":"mixed","generatedAt":"2026-11-22T01:10:20.258Z","layout":{"example":"data/train-00000-of-00002.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"504152311504151a151e4c150215001200000d30090000004d617474657267656e15001516151a2c15d00f1510150615061c360028094d617474657267656e18094d617474657267656e0000000b2803000000d00f0101d00f00150415e6bf01159894014c15ce0f1500120000f35fc0080000004b437541675362320a00000042613328436150622934090000005372284c6153322932060000004365527543320131584e6432416c3348670b0000004c61384765497233427234011b484c694c61536e4867070000005a72546c324364053c10734761476501211c486f35546c345a6e010c1c4b4c693241674635016b20546c4e693253624f360119604572416c334375320d000000436132546228536d5465322933014c145933436f506401271c4d673341675064320188484e64324d675a6e33507434040000004e61324f015720537233496e38536e33012428436132437534417333417501a03042614575427234020000005962011118437243754e6932015b1c546d38546c3242690144205262496e47653246360124104e61324572090b144c75325a6e4e0d23184e613254694638013c1c4261335372436c38012f185072595a6e5074014720546234536d4d675338018b2448663328416c4375322905be244b344167334175427231057e1c4e644d6e46655032014208593241211b01591854694d6e436f5305","encoding":"hex","key":"data/train-00000-of-00002.parquet","truncatedAt":512}],"sampleObjects":["data/train-00000-of-00002.parquet","data/train-00001-of-00002.parquet","data/validation-00000-of-00001.parquet"],"sidecars":[{"bytes":"---\nlanguage:\n- en\nlicense: cc-by-4.0\nsize_categories:\n- 100K<n<1M\npretty_name: MatterGen XRD\ndataset_info:\n  features:\n  - name: Database\n    dtype: string\n  - name: Reduced Formula\n    dtype: string\n  - name: CIF\n    dtype: string\n  - name: Condition Vector\n    dtype: string\n  splits:\n  - name: train\n    num_bytes: 760949508.0068295\n    num_examples: 591964\n  - name: validation\n    num_bytes: 84550230.99317053\n    num_examples: 65774\n  download_size: 249814282\n  dataset_size: 845499739.0\nconfigs:\n- config_name: default\n  data_files:\n  - split: train\n    path: data/train-*\n  - split: validation\n    path: data/validation-*\ntags:\n- materials-science\n- crystallography\n- cif\n---\n\n# Dataset Card for MatterGen XRD\n\nAlex-MP-20 crystal structures paired with up to 20 of their most intense simulated XRD peaks.\n\n## Dataset Details\n\n- **Curated by:** Bone et al. (University College London)\n- **Source data:** [Alex-MP-20](https://github.com/microsoft/mattergen/tree/main/data-release/alex-mp) (MatterGen, from Alexandria and MP-20)\n- **Used to train:** [c-bone/CrystaLLM-pi_Mattergen-XRD](https://huggingface.co/c-bone/CrystaLLM-pi_Mattergen-XRD)\n- **Paper:** [Discovery and recovery of crystalline materials with property-conditioned transformers (arXiv:2511.21299)](https://arxiv.org/abs/2511.21299)\n- **Repository:** [GitHub: CrystaLLM-pi](https://github.com/C-Bone-UCL/CrystaLLM-pi)\n- **License:** CC BY 4.0, following the source data\n\n## Dataset Structure\n\n| Column | Description |\n|---|---|\n| `Database` | Source database |\n| `Reduced Formula` | Reduced chemical formula |\n| `CIF` | Crystal structure in CrystaLLM-π augmented CIF format |\n| `Condition Vector` | Up to 20 of the most intense XRD peaks (CuKα), stored as 2θ positions followed by intensities, min-max normalised and padded with -100 |\n\n| Split | Rows |\n|---|---|\n| train | 591,964 |\n| validation | 65,774 |\n\n## Dataset Creation\n\nThe structures are those of [MatterGen Density](https://huggingface.co/datasets/c-bone/mattergen_den_ehull). XRD patterns were calculated with pymatgen's XRDCalculator at the CuKα wavelength. The dataset uses a random 90:10 train:validation split.\n\n## Citation\n\n```bibtex\n@misc{bone2025discoveryrecoverycrystallinematerials,\n      title={Discovery and recovery of crystalline materials with property-conditioned transformers},\n      author={Cyprien Bone and Matthew Walker and Bradley A. A. Martin and Kuangdai Leng and Luis M. Antunes and Ricardo Grau-Crespo and Amil Aligayev and Javier Dominguez and Keith T. Butler},\n      year={2025},\n      eprint={2511.21299},\n      archivePrefix={arXiv},\n      primaryClass={cond-mat.mtrl-sci},\n      url={https://arxiv.org/abs/2511.21299},\n}\n\n@article{zeni2025mattergen,\n      title={A generative model for inorganic materials design},\n      author={Zeni, Claudio and Pinsler, Robert and Z{\\\"u}gner, Daniel and Fowler, Andrew and Horton, Matthew and Fu, Xiang and Wang, Zilong and Shysheya, Aliaksandra and Crabb{\\'e}, Jonathan and Ueda, Shoko and Sordillo, Roberto and Sun, Lixin and Smith, Jake and Nguyen, Bichlien and Schulz, Hannes and Lewis, Sarah and Huang, Chin-Wei and Lu, Ziheng and Zhou, Yichi and Yang, Han and Hao, Hongxia and Li, Jielan and Yang, Chunlei and Li, Wenjie and Tomioka, Ryota and Xie, Tian},\n      journal={Nature},\n      volume={639},\n      pages={624--632},\n      year={2025},\n      doi={10.1038/s41586-025-08628-5},\n}\n\n@misc{schmidt2022alexandria,\n      title={Large-scale machine-learning-assisted exploration of the whole materials space},\n      author={Schmidt, Jonathan and Hoffmann, Noah and Wang, Hai-Chen and Borlido, Pedro and Carri{\\c{c}}o, Pedro J. M. A. and Cerqueira, Tiago F. T. and Botti, Silvana and Marques, Miguel A. L.},\n      publisher={Materials Cloud},\n      year={2022},\n      doi={10.24435/materialscloud:m7-50},\n}\n\n@article{jain2013materialsproject,\n      title={Commentary: The Materials Project: A materials genome approach to accelerating materials innovation},\n      author={Jain, Anubhav and Ong, Shyue Ping and Hautier, Geoffroy and Chen, Wei and Richards, William Davidson and Dacek, Ste","encoding":"utf8","key":"README.md","name":"README.md","size":4347,"truncated":true}],"sourceObjectKey":"data/train-00000-of-00002.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"c-bone/mattergen_XRD\")\nprint(ds)","starterSamplePath":"data/train-00000-of-00002.parquet","totalObjects":5},"summary":"Training data from University College London for CrystaLLM-pi, a property-conditioned transformer that generates crystal structures.","title":"MatterGen Alex-MP-20 Crystal Structures with Simulated XRD Peaks for Diffraction-Conditioned Generation (CrystaLLM-pi, UCL)","updatedAt":"2026-11-22T04:04:06.688Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/c-bone/mattergen_XRD"}}