{"success":true,"data":{"author":"Cesare Malosso, Michele Ceriotti, Arslan Mazitov and coauthors (EPFL COSMO); ColabFit conversion","bucketAccessType":"public","bucketName":"colabfit/Massive_Atomic_Diversity_MAD-1.5_r2SCAN_Train","bucketPrefix":"","category":"Chemistry & Materials","cloudProvider":"huggingface","createdAt":"2026-11-16T15:39:57.764Z","description":"Training split of MAD-1.5, the second version of the Massive Atomic Diversity dataset from EPFL used to train the PET-MAD universal interatomic potentials. All structures are computed with one all-electron workflow: the r2SCAN meta-GGA functional in FHI-aims (tight basis, 8 per Angstrom k-point density, 0.05 eV Gaussian smearing). It spans 102 elements and 14 subsets including bulk crystals from MC3D, rattled and random structures, surfaces, nanoclusters, 2D materials, molecular crystals and molecular fragments, with monomers, dimers and trimers all placed in training; outliers were removed by force thresholds and LLPR uncertainty filtering. ColabFit counts 180,174 configurations (about 2.6 million atoms) with energy, atomization energy, forces and stress. This is the ColabFit Exchange conversion: configurations sit in Parquet files under co/ (positions, cell, species, computed properties and metadata per row) with dataset-level information in ds.parquet; read them with pyarrow, pandas, polars or Hugging Face datasets following the ColabFit schema at materials.colabfit.org/docs. Published on Materials Cloud under CC-BY-4.0; cite Malosso et al., arXiv:2603.02089 (2026).","displayTitle":"MAD-1.5 Massive Atomic Diversity r2SCAN Training Split (102 Elements), ColabFit Conversion","doi":"10.24435/materialscloud:jc-9f","huggingFaceUrl":"https://huggingface.co/datasets/colabfit/Massive_Atomic_Diversity_MAD-1.5_r2SCAN_Train","id":"e1ca04a9-83c2-5789-ad03-1ac95462282b","license":"CC-BY-4.0","licenseEvidenceUrl":"https://archive.materialscloud.org/api/records/18tke-tt476","objectCountEstimate":6,"probeStatus":"ok","referenceUrl":"https://doi.org/10.48550/arXiv.2603.02089","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"colabfit/Massive_Atomic_Diversity_MAD-1.5_r2SCAN_Train\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"colabfit/Massive_Atomic_Diversity_MAD-1.5_r2SCAN_Train\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=colabfit, license:cc-by-4.0, size_categories:100K<n<1M, format:parquet, downloads=49"],"format":"mixed","generatedAt":"2026-11-16T15:40:10.565Z","layout":{"example":"co/co_0.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"co/co_0.parquet","truncatedAt":512}],"sampleObjects":["co/co_0.parquet","cs/cs_0.parquet","cs_co_map/cs_co_map_0.parquet","ds.parquet"],"sidecars":[{"bytes":"---\nconfigs:\n- config_name: default\n  data_files: \"co/*.parquet\"\n- config_name: info\n  data_files: \"ds.parquet\"\n- config_name: configuration_sets\n  data_files: \"cs/*.parquet\"\n- config_name: config_set_mapping\n  data_files: \"cs_co_map/*.parquet\"\nlicense: cc-by-4.0\ntags:\n- molecular dynamics\n- mlip\n- interatomic potential\npretty_name: Massive Atomic Diversity MAD-1.5 r2SCAN Train\n---\n### <details><summary>Cite this dataset </summary>Malosso, C., Bigi, F., Pegolo, P., Abbott, J. W., Loche, P., Rossi, M., Ceriotti, M., and Mazitov, A. _Massive Atomic Diversity MAD-1.5 r2SCAN Train_. ColabFit, 2026. https://doi.org/None</details>  \n#### This dataset has been curated and formatted for the ColabFit Exchange  \n#### This dataset is also available on the ColabFit Exchange:  \nhttps://materials.colabfit.org/id/DS_okaut8m5c2vk_0  \n#### Visit the ColabFit Exchange to search additional datasets by author, description, element content and more.  \nhttps://materials.colabfit.org\n<br><hr>  \n# Dataset  Name  \nMassive Atomic Diversity MAD-1.5 r2SCAN Train  \n### Description  \nTraining split of the MAD-1.5 (Massive Atomic Diversity version 1.5) dataset, a highly curated collection designed for training broadly applicable atomistic machine-learning models across the full periodic table. MAD-1.5 extends the original MAD dataset with targeted enrichment strategies covering 102 chemical elements (all isotopes with half-life above one day). All 216,803 structures are computed with a single standardized all-electron DFT workflow using the r2SCAN meta-GGA functional in FHI-aims (version 250806), with tight basis sets, 8 Angstrom^-1 k-point density, Gaussian smearing of 0.05 eV, and SCF convergence thresholds of 1e-6 eV (energy), 1e-4 eV/Angstrom (forces), and 1e-5 e*a0^-3 (electron density). The dataset spans molecules (monomers, dimers, trimers, molecular crystals), bulk crystals, surfaces, nanoclusters, and low-dimensional structures organized into 14 subsets. Quality is ensured by two-step outlier removal: heuristic filtering of structures with forces >100 eV/Angstrom, followed by LLPR uncertainty-based filtering. The training split (~83% of cleaned data) includes all monomers, dimers, and trimers to anchor low-body-order interactions. A companion PBE-functional dataset (Massive_Atomic_Diversity_MAD-1.5_PBE) was used during model training with separate prediction heads.  \n### Dataset authors  \nCesare Malosso, Filippo Bigi, Paolo Pegolo, Joseph W. Abbott, Philip Loche, Mariana Rossi, Michele Ceriotti, Arslan Mazitov  \n### Publication  \nhttps://doi.org/10.48550/arXiv.2603.02089  \n### Original data link  \nhttps://doi.org/10.24435/materialscloud:jc-9f  \n### License  \nCC-BY-4.0  \n### Number of unique molecular configurations  \n180174  \n### Number of atoms  \n2630122  \n### Elements included  \nAc, Ag, Al, Am, Ar, As, At, Au, B, Ba, Be, Bi, Bk, Br, C, Ca, Cd, Ce, Cf, Cl, Cm, Co, Cr, Cs, Cu, Dy, Er, Es, Eu, F, Fe, Fm, Fr, Ga, Gd, Ge, H, He, Hf, Hg, Ho, I, In, Ir, K, Kr, La, Li, Lu, Md, Mg, Mn, Mo, N, Na, Nb, Nd, Ne, Ni, No, Np, O, Os, P, Pa, Pb, Pd, Pm, Po, Pr, Pt, Pu, Ra, Rb, Re, Rh, Rn, Ru, S, Sb, Sc, Se, Si, Sm, Sn, Sr, Ta, Tb, Tc, Te, Th, Ti, Tl, Tm, U, V, W, Xe, Y, Yb, Zn, Zr  \n### Properties included  \nenergy, atomization energy, atomic forces, cauchy stress  \n<br>\n<hr>  \n\n# Usage  \n- `ds.parquet` : Aggregated dataset information.  \n- `co/` directory: Configuration rows each include a structure, calculated properties, and metadata.  \n- `cs/` directory : Configuration sets are subsets of configurations grouped by some common characteristic. If `cs/` does not exist, no configurations sets have been defined for this dataset.  \n- `cs_co_map/` directory : The mapping of configurations to configuration sets (if defined).  \n<br>\n#### ColabFit Exchange documentation includes descriptions of content and example code for parsing parquet files:  \n- [Parquet parsing: example code](https://materials.colabfit.org/docs/how_to_use_parquet)  \n- [Dataset info schema](https://materials.colabfit.org/docs/dataset_schema)  \n- [Configuration schema](https://materials.colabf","encoding":"utf8","key":"README.md","name":"README.md","size":4339,"truncated":true}],"sourceObjectKey":"co/co_0.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"colabfit/Massive_Atomic_Diversity_MAD-1.5_r2SCAN_Train\")\nprint(ds)","starterSamplePath":"co/co_0.parquet","totalObjects":6},"summary":"Training split of MAD-1.5, the second version of the Massive Atomic Diversity dataset from EPFL used to train the PET-MAD universal interatomic potentials.","title":"MAD-1.5 Massive Atomic Diversity r2SCAN Training Split (102 Elements), ColabFit Conversion","updatedAt":"2026-11-17T17:03:11.522Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/colabfit/Massive_Atomic_Diversity_MAD-1.5_r2SCAN_Train"}}