{"url":"/task/formation-energy","name":"Formation Energy","slug":"formation-energy","description_markdown":"On the QM9 dataset the numbers reported in the table are the mean absolute error in eV on the target variable U0 divided by U0's chemical accuracy, which is equal to 0.043.","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":54,"papers_with_code":31,"benchmarks":14,"benchmark_tables_in_archive":14,"benchmark_tables_shown":14,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/formation-energy-on-qm9","slug":"formation-energy-on-qm9","dataset":"QM9","dataset_url":"/dataset/qm9","rows_in_archive":18,"metrics":["MAE"],"first_row_in_archive_order":{"model":"TensorNet","paper_title":"TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials","paper_url":"/paper/tensornet-cartesian-tensor-representations","paper_date":"2023-06-10","arxiv_id":"2306.06482","code_links":[{"title":"torchmd/torchmd-net","url":"https://github.com/torchmd/torchmd-net"},{"title":"materialsvirtuallab/matgl","url":"https://github.com/materialsvirtuallab/matgl"},{"title":"jla-gardner/graph-pes","url":"https://github.com/jla-gardner/graph-pes"}],"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/formation-energy-on-materials-project","slug":"formation-energy-on-materials-project","dataset":"Materials Project","dataset_url":"/dataset/materials-project","rows_in_archive":9,"metrics":["MAE"],"first_row_in_archive_order":{"model":"CartNet","paper_title":"A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid Estimation","paper_url":"/paper/a-cartesian-encoding-graph-neural-network-for","paper_date":"2025-01-30","arxiv_id":"2501.18369","code_links":[{"title":"imatge-upc/CartNet","url":"https://github.com/imatge-upc/CartNet"}],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-jarvis-dft-formation","slug":"formation-energy-on-jarvis-dft-formation","dataset":"JARVIS-DFT","dataset_url":"/dataset/jarvis-dft-formation-energy","rows_in_archive":6,"metrics":["MAE"],"first_row_in_archive_order":{"model":"CartNet","paper_title":"A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid Estimation","paper_url":"/paper/a-cartesian-encoding-graph-neural-network-for","paper_date":"2025-01-30","arxiv_id":"2501.18369","code_links":[{"title":"imatge-upc/CartNet","url":"https://github.com/imatge-upc/CartNet"}],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-3bpa","slug":"formation-energy-on-3bpa","dataset":"3BPA","dataset_url":null,"rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"BOTNet","paper_title":"EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations","paper_url":"/paper/egraffbench-evaluation-of-equivariant-graph","paper_date":"2023-10-03","arxiv_id":"2310.02428","code_links":[],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-acetylacetone","slug":"formation-energy-on-acetylacetone","dataset":"Acetylacetone","dataset_url":null,"rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"BOTNet","paper_title":"EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations","paper_url":"/paper/egraffbench-evaluation-of-equivariant-graph","paper_date":"2023-10-03","arxiv_id":"2310.02428","code_links":[],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-aspirin","slug":"formation-energy-on-aspirin","dataset":"Aspirin","dataset_url":null,"rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"Allegro","paper_title":"EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations","paper_url":"/paper/egraffbench-evaluation-of-equivariant-graph","paper_date":"2023-10-03","arxiv_id":"2310.02428","code_links":[],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-ethanol","slug":"formation-energy-on-ethanol","dataset":"Ethanol","dataset_url":null,"rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"MACE","paper_title":"EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations","paper_url":"/paper/egraffbench-evaluation-of-equivariant-graph","paper_date":"2023-10-03","arxiv_id":"2310.02428","code_links":[],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-gete","slug":"formation-energy-on-gete","dataset":"GeTe","dataset_url":null,"rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"BOTNet","paper_title":"EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations","paper_url":"/paper/egraffbench-evaluation-of-equivariant-graph","paper_date":"2023-10-03","arxiv_id":"2310.02428","code_links":[],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-lips","slug":"formation-energy-on-lips","dataset":"LiPS","dataset_url":null,"rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"NequIP","paper_title":"EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations","paper_url":"/paper/egraffbench-evaluation-of-equivariant-graph","paper_date":"2023-10-03","arxiv_id":"2310.02428","code_links":[],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-lips20","slug":"formation-energy-on-lips20","dataset":"LiPS20","dataset_url":null,"rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"Allegro","paper_title":"EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations","paper_url":"/paper/egraffbench-evaluation-of-equivariant-graph","paper_date":"2023-10-03","arxiv_id":"2310.02428","code_links":[],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-naphthalene","slug":"formation-energy-on-naphthalene","dataset":"Naphthalene","dataset_url":null,"rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"BOTNet","paper_title":"EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations","paper_url":"/paper/egraffbench-evaluation-of-equivariant-graph","paper_date":"2023-10-03","arxiv_id":"2310.02428","code_links":[],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-oqm9hk","slug":"formation-energy-on-oqm9hk","dataset":"OQM9HK","dataset_url":"/dataset/oqm9hk","rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"CGNN Full Ensemble","paper_title":"OQM9HK: A Large-Scale Graph Dataset for Machine Learning in Materials Science","paper_url":"/paper/oqm9hk-a-large-scale-graph-dataset-for","paper_date":"2022-09-30","arxiv_id":null,"code_links":[{"title":"Tony-Y/cgnn","url":"https://github.com/Tony-Y/cgnn"}],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-oqmd-v12","slug":"formation-energy-on-oqmd-v12","dataset":"OQMD v1.2","dataset_url":"/dataset/oqmd-v1-2","rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"CGNN Ensemble","paper_title":"Crystal Graph Neural Networks for Data Mining in Materials Science","paper_url":"/paper/crystal-graph-neural-networks-for-data-mining","paper_date":"2019-05-27","arxiv_id":null,"code_links":[{"title":"Tony-Y/cgnn","url":"https://github.com/Tony-Y/cgnn"}],"syntology":null}},{"leaderboard":"/sota/formation-energy-on-salicylic-acid","slug":"formation-energy-on-salicylic-acid","dataset":"Salicylic Acid","dataset_url":null,"rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"MACE","paper_title":"EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulations","paper_url":"/paper/egraffbench-evaluation-of-equivariant-graph","paper_date":"2023-10-03","arxiv_id":"2310.02428","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/materials-project","name":"Materials Project","full_name":"","num_papers_in_archive":157},{"url":"/dataset/md17","name":"MD17","full_name":"Molecular Dynamics 17","num_papers_in_archive":105},{"url":"/dataset/qm9","name":"QM9","full_name":"","num_papers_in_archive":76},{"url":"/dataset/jarvis-dft-formation-energy","name":"JARVIS-DFT","full_name":"","num_papers_in_archive":21},{"url":"/dataset/matbench","name":"Matbench","full_name":"","num_papers_in_archive":11},{"url":"/dataset/oqmd-v1-2","name":"OQMD v1.2","full_name":"The Open Quantum Materials Database","num_papers_in_archive":3},{"url":"/dataset/oqm9hk","name":"OQM9HK","full_name":"","num_papers_in_archive":2},{"url":"/dataset/wbm","name":"WBM","full_name":"Predicting stable crystalline compounds using chemical similarity","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/atomistic-description","name":"Atomistic Description"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":31,"tagged_in_all":54,"items":[{"url":"/paper/neural-message-passing-for-quantum-chemistry","title":"Neural Message Passing for Quantum Chemistry","date":"2017-04-04","arxiv_id":"1704.01212","repositories_listed":20,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/neural-message-passing-with-edge-updates-for","title":"Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials","date":"2018-06-08","arxiv_id":"1806.03146","repositories_listed":5,"syntology":{"n":22,"n_ran":4,"n_unverified":18,"n_pointer_only":4}},{"url":"/paper/schnet-a-continuous-filter-convolutional","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","date":"2017-06-26","arxiv_id":"1706.08566","repositories_listed":5,"syntology":null},{"url":"/paper/directional-message-passing-for-molecular-1","title":"Directional Message Passing for Molecular Graphs","date":"2020-03-06","arxiv_id":"2003.03123","repositories_listed":4,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":3}},{"url":"/paper/matbench-discovery-an-evaluation-framework","title":"Matbench Discovery -- A framework to evaluate machine learning crystal stability predictions","date":"2023-08-28","arxiv_id":"2308.14920","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/tensornet-cartesian-tensor-representations","title":"TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials","date":"2023-06-10","arxiv_id":"2306.06482","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/molecular-mechanics-driven-graph-neural","title":"Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures","date":"2020-11-15","arxiv_id":"2011.07457","repositories_listed":3,"syntology":null},{"url":"/paper/scalable-gaussian-process-regression-enables","title":"Linear-scaling kernels for protein sequences and small molecules outperform deep learning while providing uncertainty quantitation and improved interpretability","date":"2023-02-07","arxiv_id":"2302.03294","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/periodic-graph-transformers-for-crystal","title":"Periodic Graph Transformers for Crystal Material Property Prediction","date":"2022-09-23","arxiv_id":"2209.11807","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/materials-property-prediction-using-symmetry","title":"Materials property prediction using symmetry-labeled graphs as atomic-position independent descriptors","date":"2019-05-15","arxiv_id":"1905.06048","repositories_listed":2,"syntology":null},{"url":"/paper/automat-enabling-automated-crystal-structure","title":"AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use","date":"2025-05-19","arxiv_id":"2505.12650","repositories_listed":1,"syntology":null},{"url":"/paper/invdesflow-al-active-learning-based-workflow","title":"InvDesFlow-AL: Active Learning-based Workflow for Inverse Design of Functional Materials","date":"2025-05-14","arxiv_id":"2505.09203","repositories_listed":1,"syntology":null},{"url":"/paper/matmmfuse-multi-modal-fusion-model-for","title":"MatMMFuse: Multi-Modal Fusion model for Material Property Prediction","date":"2025-04-30","arxiv_id":"2505.04634","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/a-cartesian-encoding-graph-neural-network-for","title":"A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid Estimation","date":"2025-01-30","arxiv_id":"2501.18369","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-the-power-of-novel-conditional","title":"Unleashing the power of novel conditional generative approaches for new materials discovery","date":"2024-11-05","arxiv_id":"2411.03156","repositories_listed":1,"syntology":null},{"url":"/paper/establishing-deep-infomax-as-an-effective","title":"Establishing Deep InfoMax as an effective self-supervised learning methodology in materials informatics","date":"2024-06-30","arxiv_id":"2407.00671","repositories_listed":1,"syntology":null},{"url":"/paper/crystal-lsbo-automated-design-of-de-novo","title":"Crystal-LSBO: Automated Design of De Novo Crystals with Latent Space Bayesian Optimization","date":"2024-05-28","arxiv_id":"2405.17881","repositories_listed":1,"syntology":null},{"url":"/paper/pushing-the-pareto-front-of-band-gap-and","title":"Pushing the Pareto front of band gap and permittivity: ML-guided search for dielectric materials","date":"2024-01-11","arxiv_id":"2401.05848","repositories_listed":1,"syntology":null},{"url":"/paper/crystal-gfn-sampling-crystals-with-desirable","title":"Crystal-GFN: sampling crystals with desirable properties and constraints","date":"2023-10-07","arxiv_id":"2310.04925","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-approximations-of-complete","title":"Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction","date":"2023-06-12","arxiv_id":"2306.10045","repositories_listed":1,"syntology":null},{"url":"/paper/crysgnn-distilling-pre-trained-knowledge-to","title":"CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials","date":"2023-01-14","arxiv_id":"2301.05852","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/discovery-of-2d-materials-using-transformer","title":"Discovery of 2D materials using Transformer Network based Generative Design","date":"2023-01-14","arxiv_id":"2301.05824","repositories_listed":1,"syntology":null},{"url":"/paper/materials-property-prediction-with","title":"Materials Property Prediction with Uncertainty Quantification: A Benchmark Study","date":"2022-11-04","arxiv_id":"2211.02235","repositories_listed":1,"syntology":null},{"url":"/paper/oqm9hk-a-large-scale-graph-dataset-for","title":"OQM9HK: A Large-Scale Graph Dataset for Machine Learning in Materials Science","date":"2022-09-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/physics-guided-generative-adversarial-1","title":"Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints","date":"2022-03-27","arxiv_id":"2203.14352","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/semi-supervised-teacher-student-deep-neural","title":"Semi-supervised teacher-student deep neural network for materials discovery","date":"2021-12-12","arxiv_id":"2112.06142","repositories_listed":1,"syntology":null},{"url":"/paper/distributed-representations-of-atoms-and","title":"Distributed Representations of Atoms and Materials for Machine Learning","date":"2021-07-30","arxiv_id":"2107.14664","repositories_listed":1,"syntology":null},{"url":"/paper/heterogeneous-molecular-graph-neural-networks","title":"Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties","date":"2020-09-26","arxiv_id":"2009.12710","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/crystal-graph-neural-networks-for-data-mining","title":"Crystal Graph Neural Networks for Data Mining in Materials Science","date":"2019-05-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dscribe-library-of-descriptors-for-machine","title":"DScribe: Library of Descriptors for Machine Learning in Materials Science","date":"2019-04-18","arxiv_id":"1904.08875","repositories_listed":1,"syntology":null}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}