{"url":"/dataset/pcqm4mv2-lsc","name":"PCQM4Mv2-LSC","full_name":null,"description_markdown":"PCQM4Mv2 is a quantum chemistry dataset originally curated under the PubChemQC project. Based on the PubChemQC, we define a meaningful ML task of predicting DFT-calculated HOMO-LUMO energy gap of molecules given their 2D molecular graphs. The HOMO-LUMO gap is one of the most practically-relevant quantum chemical properties of molecules since it is related to reactivity, photoexcitation, and charge transport. Moreover, predicting the quantum chemical property only from 2D molecular graphs without their 3D equilibrium structures is also practically favorable. This is because obtaining 3D equilibrium structures requires DFT-based geometry optimization, which is expensive on its own.","description_withheld":null,"homepage":"https://ogb.stanford.edu/docs/lsc/pcqm4mv2/","introduced_date":"2021-03-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/ogb-lsc-a-large-scale-challenge-for-machine","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","first_author":"Weihua Hu","url":null},"license":{"name":"CC BY 4.0","url":null},"modalities":[],"tasks":[{"name":"Graph Regression","url":"/task/graph-regression","datasets_with_task":"/datasets/task/graph-regression"},{"name":"Graph Property Prediction","url":"/task/graph-property-prediction","datasets_with_task":"/datasets/task/graph-property-prediction"}],"languages":[],"variants":["PCQM4Mv2-LSC"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/graph-regression-on-pcqm4mv2-lsc","task":"Graph Regression","dataset_variant":"PCQM4Mv2-LSC","rows":20,"metrics":["Validation MAE","Test MAE"],"first_row_in_archive_order":{"model":"ESA (Edge set attention, no positional encodings)","paper":"/paper/masked-attention-is-all-you-need-for-graphs","metrics":{"Test MAE":"N/A","Validation MAE":"0.0235"},"code_links":[{"title":"davidbuterez/edge-set-attention","url":"https://github.com/davidbuterez/edge-set-attention"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/masked-attention-is-all-you-need-for-graphs","title":"An end-to-end attention-based approach for learning on graphs","date":"2024-02-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/triplet-interaction-improves-graph","title":"Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers","date":"2024-02-07","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":10,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/topology-informed-graph-transformer","title":"Topology-Informed Graph Transformer","date":"2024-02-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":14,"samples_unverified":7,"pointer_only_for_licence":21,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/graph-convolutions-enrich-the-self-attention","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","date":"2023-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":29,"samples_ran":19,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-information-pathways-hypothesis","title":"The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles","date":"2023-06-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/graph-inductive-biases-in-transformers","title":"Graph Inductive Biases in Transformers without Message Passing","date":"2023-05-27","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":6,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/graph-propagation-transformer-for-graph","title":"Graph Propagation Transformer for Graph Representation Learning","date":"2023-05-19","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/highly-accurate-quantum-chemical-property","title":"Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+","date":"2023-03-16","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/one-transformer-can-understand-both-2d-3d","title":"One Transformer Can Understand Both 2D & 3D Molecular Data","date":"2022-10-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pure-transformers-are-powerful-graph-learners","title":"Pure Transformers are Powerful Graph Learners","date":"2022-07-06","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":7,"samples_unverified":0,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/recipe-for-a-general-powerful-scalable-graph","title":"Recipe for a General, Powerful, Scalable Graph Transformer","date":"2022-05-25","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":3,"samples_unverified":18,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/graph-self-attention-for-learning-graph","title":"GRPE: Relative Positional Encoding for Graph Transformer","date":"2022-01-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/edge-augmented-graph-transformers-global-self","title":"Global Self-Attention as a Replacement for Graph Convolution","date":"2021-08-07","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/do-transformers-really-perform-bad-for-graph","title":"Do Transformers Really Perform Bad for Graph Representation?","date":"2021-06-09","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/ogb-lsc-a-large-scale-challenge-for-machine","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","date":"2021-03-17","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/how-powerful-are-graph-neural-networks","title":"How Powerful are Graph Neural Networks?","date":"2018-10-01","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":3,"samples_unverified":7,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semi-supervised-classification-with-graph","title":"Semi-Supervised Classification with Graph Convolutional Networks","date":"2016-09-09","rows_on_this_dataset":1,"code_links":55,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":58,"samples_ran":31,"samples_unverified":27,"pointer_only_for_licence":22,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":13,"samples_harvested":191,"samples_ran":98,"samples_unverified":93,"pointer_only_for_licence":63,"papers_with_no_sample_that_ran":3,"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."}