{"url":"/dataset/chili-100k","name":"CHILI-100K","full_name":null,"description_markdown":"The CHILI-100K dataset is a large-scale graph dataset (with overall >183M nodes, >1.2B edges) of nanomaterials generated from experimentally determined crystal structures. The crystal structures used in CHILI-100K are obtained from a curated subset from the Crystallography Open Database (COD) and has a broad chemical scope covering database entries for 68 metals and 11 non-metals.","description_withheld":null,"homepage":"https://github.com/UlrikFriisJensen/CHILI","introduced_date":"2024-02-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/chili-chemically-informed-large-scale","title":"CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learning","first_author":"Ulrik Friis-Jensen","url":null},"license":{"name":"Apache-2.0","url":"https://opensource.org/license/apache-2-0/"},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Atomic number classification","url":"/task/atomic-number-classification","datasets_with_task":"/datasets/task/atomic-number-classification"},{"name":"Crystal system classification","url":"/task/crystal-system-classification","datasets_with_task":"/datasets/task/crystal-system-classification"},{"name":"Space group classification","url":"/task/space-group-classification","datasets_with_task":"/datasets/task/space-group-classification"},{"name":"Position regression","url":"/task/position-regression","datasets_with_task":"/datasets/task/position-regression"},{"name":"Distance regression","url":"/task/distance-regression","datasets_with_task":"/datasets/task/distance-regression"},{"name":"SAXS regression","url":"/task/saxs-regression","datasets_with_task":"/datasets/task/saxs-regression"},{"name":"XRD regression","url":"/task/xrd-regression","datasets_with_task":"/datasets/task/xrd-regression"},{"name":"X-ray PDF regression","url":"/task/x-ray-pdf-regression","datasets_with_task":"/datasets/task/x-ray-pdf-regression"},{"name":"SANS regression","url":"/task/sans-regression","datasets_with_task":"/datasets/task/sans-regression"},{"name":"ND regression","url":"/task/nd-regression","datasets_with_task":"/datasets/task/nd-regression"},{"name":"Neutron PDF regression","url":"/task/neutron-pdf-regression","datasets_with_task":"/datasets/task/neutron-pdf-regression"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CHILI-100K"],"data_loaders":[{"repo":"https://github.com/UlrikFriisJensen/CHILI","url":"https://github.com/UlrikFriisJensen/CHILI","frameworks":["pytorch"]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/atomic-number-classification-on-chili-100k","task":"Atomic number classification","dataset_variant":"CHILI-100K","rows":9,"metrics":["F1-score (Weighted)"],"first_row_in_archive_order":{"model":"EdgeCNN","paper":"/paper/chili-chemically-informed-large-scale","metrics":{"F1-score (Weighted)":"0.572 +/- 0.017"},"code_links":[{"title":"UlrikFriisJensen/CHILI","url":"https://github.com/UlrikFriisJensen/CHILI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/crystal-system-classification-on-chili-100k","task":"Crystal system classification","dataset_variant":"CHILI-100K","rows":9,"metrics":["F1-score (Weighted)"],"first_row_in_archive_order":{"model":"Random","paper":"/paper/chili-chemically-informed-large-scale","metrics":{"F1-score (Weighted)":"0.168 +/- 0.014"},"code_links":[{"title":"UlrikFriisJensen/CHILI","url":"https://github.com/UlrikFriisJensen/CHILI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/space-group-classification-on-chili-100k","task":"Space group classification","dataset_variant":"CHILI-100K","rows":9,"metrics":["F1-score (Weighted)"],"first_row_in_archive_order":{"model":"EdgeCNN","paper":"/paper/chili-chemically-informed-large-scale","metrics":{"F1-score (Weighted)":"0.158 +/- 0.035"},"code_links":[{"title":"UlrikFriisJensen/CHILI","url":"https://github.com/UlrikFriisJensen/CHILI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/distance-regression-on-chili-100k","task":"Distance regression","dataset_variant":"CHILI-100K","rows":8,"metrics":["MSE "],"first_row_in_archive_order":{"model":"EdgeCNN","paper":"/paper/chili-chemically-informed-large-scale","metrics":{"MSE ":"0.030 +/- 0.001"},"code_links":[{"title":"UlrikFriisJensen/CHILI","url":"https://github.com/UlrikFriisJensen/CHILI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/position-regression-on-chili-100k","task":"Position regression","dataset_variant":"CHILI-100K","rows":8,"metrics":["Positional MAE"],"first_row_in_archive_order":{"model":"GraphUNet","paper":"/paper/chili-chemically-informed-large-scale","metrics":{"Positional MAE":"14.824 +/- 0.315"},"code_links":[{"title":"UlrikFriisJensen/CHILI","url":"https://github.com/UlrikFriisJensen/CHILI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/saxs-regression-on-chili-100k","task":"SAXS regression","dataset_variant":"CHILI-100K","rows":8,"metrics":["MSE "],"first_row_in_archive_order":{"model":"PMLP","paper":"/paper/chili-chemically-informed-large-scale","metrics":{"MSE ":"0.003 +/- 0.000"},"code_links":[{"title":"UlrikFriisJensen/CHILI","url":"https://github.com/UlrikFriisJensen/CHILI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/x-ray-pdf-regression-on-chili-100k","task":"X-ray PDF regression","dataset_variant":"CHILI-100K","rows":8,"metrics":["MSE "],"first_row_in_archive_order":{"model":"Mean","paper":"/paper/chili-chemically-informed-large-scale","metrics":{"MSE ":"0.007"},"code_links":[{"title":"UlrikFriisJensen/CHILI","url":"https://github.com/UlrikFriisJensen/CHILI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/xrd-regression-on-chili-100k","task":"XRD regression","dataset_variant":"CHILI-100K","rows":8,"metrics":["MSE "],"first_row_in_archive_order":{"model":"EdgeCNN","paper":"/paper/chili-chemically-informed-large-scale","metrics":{"MSE ":"0.006 +/- 0.000"},"code_links":[{"title":"UlrikFriisJensen/CHILI","url":"https://github.com/UlrikFriisJensen/CHILI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/chili-chemically-informed-large-scale","title":"CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learning","date":"2024-02-20","rows_on_this_dataset":67,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}