{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OIIXKO3JBYVDR3CPM7FOYBMP3S","short_pith_number":"pith:OIIXKO3J","schema_version":"1.0","canonical_sha256":"7211753b690e2a38ec4f67caec058fdca2c005c0deda1ab4210216c6ff173c76","source":{"kind":"arxiv","id":"2206.07697","version":2},"attestation_state":"computed","paper":{"title":"MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.LG","physics.chem-ph"],"primary_cat":"stat.ML","authors_text":"Christoph Ortner, D\\'avid P\\'eter Kov\\'acs, G\\'abor Cs\\'anyi, Gregor N. C. Simm, Ilyes Batatia","submitted_at":"2022-06-15T17:46:05Z","abstract_excerpt":"Creating fast and accurate force fields is a long-standing challenge in computational chemistry and materials science. Recently, several equivariant message passing neural networks (MPNNs) have been shown to outperform models built using other approaches in terms of accuracy. However, most MPNNs suffer from high computational cost and poor scalability. We propose that these limitations arise because MPNNs only pass two-body messages leading to a direct relationship between the number of layers and the expressivity of the network. In this work, we introduce MACE, a new equivariant MPNN model th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.07697","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-06-15T17:46:05Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.LG","physics.chem-ph"],"title_canon_sha256":"705123ce308c2f81c9b83231edc4f972622f310c6ec379eb7611f9ed3d743935","abstract_canon_sha256":"2c1090b1ee9ea2129b48a49b5538c9e3c5270e52834a493d438f8d159a22bdb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:16.935390Z","signature_b64":"pcCbkaK2nFGClojbmkQPBN4xH6SPeHp2jGZmUG9h9CwGhggBWlFFMGoEMsJxl9ClHfxqoFMsAfs3xr/c8gk0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7211753b690e2a38ec4f67caec058fdca2c005c0deda1ab4210216c6ff173c76","last_reissued_at":"2026-07-05T05:36:16.934909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:16.934909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.LG","physics.chem-ph"],"primary_cat":"stat.ML","authors_text":"Christoph Ortner, D\\'avid P\\'eter Kov\\'acs, G\\'abor Cs\\'anyi, Gregor N. C. Simm, Ilyes Batatia","submitted_at":"2022-06-15T17:46:05Z","abstract_excerpt":"Creating fast and accurate force fields is a long-standing challenge in computational chemistry and materials science. Recently, several equivariant message passing neural networks (MPNNs) have been shown to outperform models built using other approaches in terms of accuracy. However, most MPNNs suffer from high computational cost and poor scalability. We propose that these limitations arise because MPNNs only pass two-body messages leading to a direct relationship between the number of layers and the expressivity of the network. In this work, we introduce MACE, a new equivariant MPNN model th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07697","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.07697/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.07697","created_at":"2026-07-05T05:36:16.934977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07697v2","created_at":"2026-07-05T05:36:16.934977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07697","created_at":"2026-07-05T05:36:16.934977+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIIXKO3JBYVD","created_at":"2026-07-05T05:36:16.934977+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIIXKO3JBYVDR3CP","created_at":"2026-07-05T05:36:16.934977+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIIXKO3J","created_at":"2026-07-05T05:36:16.934977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":36,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24922","citing_title":"Constraint-Aware Quantum Optimization of Defect Configurations in Doped ZrO2: XY-Mixer QAOA and Grover Adaptive Search","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21311","citing_title":"Property-Specific Molecular Representations via Feature-Space Transfer Compression","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23725","citing_title":"Computational references are not experiments: pre-registered validation of machine-learned sodium-cathode voltages","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10349","citing_title":"Magnetic HIP-NN for spin dynamics in disordered itinerant magnets","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09480","citing_title":"Loss-Guided Adaptive Scale Refinement for Molecular Force Prediction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15332","citing_title":"Disorder-driven symmetry suppression by van der Waals planar defects in a magnetic topological insulator","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30870","citing_title":"Adaptive fine-tuning of foundation models for crystal structure prediction: Discovery of high-pressure phases in the CaFeNi system","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24073","citing_title":"Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23725","citing_title":"Computational references are not experiments: pre-registered validation of machine-learned sodium-cathode voltages","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27864","citing_title":"A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\\mathrm{O}(2)$","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27864","citing_title":"A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\\mathrm{O}(2)$","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26834","citing_title":"A Hybrid Quantum Mechanics Machine Learning Forcefield (QM/ML) Framework for Accurate Solute-Dislocation Interaction Simulations","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22698","citing_title":"Machine Learning Interatomic Potentials: Advancing Open-Source Software for Efficient and Scalable Molecular Simulation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2507.06929","citing_title":"Machine-Learned Force Fields for Lattice Dynamics at Coupled-Cluster Level Accuracy","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20785","citing_title":"Anisotropic Crystallization Kinetics and Interfacial Dynamics of Phase-Change Material Sb$_2$S$_3$ from Machine Learning Force Field Simulations","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15630","citing_title":"Reweighting free energy profiles between universal machine learning interatomic potentials for fast consensus building","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13788","citing_title":"Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03964","citing_title":"Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20635","citing_title":"Reducing Self-Interaction Error in Transition-Metal Oxides with Different Exact-Exchange Fractions for Energy and Density","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03046","citing_title":"Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2510.05020","citing_title":"Comparing fine-tuning strategies of MACE machine learning force field for modeling Li-ion diffusion in LiF for batteries","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00185","citing_title":"QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15073","citing_title":"Fast contracted Clebsch--Gordan tensor products for equivariant graph neural networks","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13788","citing_title":"Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03464","citing_title":"Electron dynamics mediate the water-carbon {\\pi} bond","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OIIXKO3JBYVDR3CPM7FOYBMP3S","json":"https://pith.science/pith/OIIXKO3JBYVDR3CPM7FOYBMP3S.json","graph_json":"https://pith.science/api/pith-number/OIIXKO3JBYVDR3CPM7FOYBMP3S/graph.json","events_json":"https://pith.science/api/pith-number/OIIXKO3JBYVDR3CPM7FOYBMP3S/events.json","paper":"https://pith.science/paper/OIIXKO3J"},"agent_actions":{"view_html":"https://pith.science/pith/OIIXKO3JBYVDR3CPM7FOYBMP3S","download_json":"https://pith.science/pith/OIIXKO3JBYVDR3CPM7FOYBMP3S.json","view_paper":"https://pith.science/paper/OIIXKO3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07697&json=true","fetch_graph":"https://pith.science/api/pith-number/OIIXKO3JBYVDR3CPM7FOYBMP3S/graph.json","fetch_events":"https://pith.science/api/pith-number/OIIXKO3JBYVDR3CPM7FOYBMP3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIIXKO3JBYVDR3CPM7FOYBMP3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIIXKO3JBYVDR3CPM7FOYBMP3S/action/storage_attestation","attest_author":"https://pith.science/pith/OIIXKO3JBYVDR3CPM7FOYBMP3S/action/author_attestation","sign_citation":"https://pith.science/pith/OIIXKO3JBYVDR3CPM7FOYBMP3S/action/citation_signature","submit_replication":"https://pith.science/pith/OIIXKO3JBYVDR3CPM7FOYBMP3S/action/replication_record"}},"created_at":"2026-07-05T05:36:16.934977+00:00","updated_at":"2026-07-05T05:36:16.934977+00:00"}