{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4CD52RFJZC4LL55YSMC4TDGFSP","short_pith_number":"pith:4CD52RFJ","schema_version":"1.0","canonical_sha256":"e087dd44a9c8b8b5f7b89305c98cc593ffd3a0aa25cb08bec5f076089a92735d","source":{"kind":"arxiv","id":"2207.09453","version":1},"attestation_state":"computed","paper":{"title":"e3nn: Euclidean Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Mario Geiger, Tess Smidt","submitted_at":"2022-07-18T21:19:40Z","abstract_excerpt":"We present e3nn, a generalized framework for creating E(3) equivariant trainable functions, also known as Euclidean neural networks. e3nn naturally operates on geometry and geometric tensors that describe systems in 3D and transform predictably under a change of coordinate system. The core of e3nn are equivariant operations such as the TensorProduct class or the spherical harmonics functions that can be composed to create more complex modules such as convolutions and attention mechanisms. These core operations of e3nn can be used to efficiently articulate Tensor Field Networks, 3D Steerable CN"},"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":"2207.09453","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-18T21:19:40Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"75da260aa939e1bc81b0e18e6829ab7691ec8dd641e85022bf3ae8d0acb52cd0","abstract_canon_sha256":"c07d7d113dd883d6a677b0057853c002193d38e2303dd3dfe14ed3e04114942c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:57.960328Z","signature_b64":"GN0BZ9WL7MqSRd08FLGBMswpvp2RmcDS/Fcvs52q44iMoXoNUWHzsuq8v0K96TORwdTfMxE0oP3ScSCtcJsJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e087dd44a9c8b8b5f7b89305c98cc593ffd3a0aa25cb08bec5f076089a92735d","last_reissued_at":"2026-07-05T04:41:57.959924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:57.959924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"e3nn: Euclidean Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Mario Geiger, Tess Smidt","submitted_at":"2022-07-18T21:19:40Z","abstract_excerpt":"We present e3nn, a generalized framework for creating E(3) equivariant trainable functions, also known as Euclidean neural networks. e3nn naturally operates on geometry and geometric tensors that describe systems in 3D and transform predictably under a change of coordinate system. The core of e3nn are equivariant operations such as the TensorProduct class or the spherical harmonics functions that can be composed to create more complex modules such as convolutions and attention mechanisms. These core operations of e3nn can be used to efficiently articulate Tensor Field Networks, 3D Steerable CN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09453","kind":"arxiv","version":1},"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/2207.09453/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":"2207.09453","created_at":"2026-07-05T04:41:57.959969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.09453v1","created_at":"2026-07-05T04:41:57.959969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09453","created_at":"2026-07-05T04:41:57.959969+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CD52RFJZC4L","created_at":"2026-07-05T04:41:57.959969+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CD52RFJZC4LL55Y","created_at":"2026-07-05T04:41:57.959969+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CD52RFJ","created_at":"2026-07-05T04:41:57.959969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06634","citing_title":"When Do Geometric Algebra Layers Beat Scalarization? A Controlled Study on SO(3)-Equivariant Vector Laws","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25853","citing_title":"A Combined Tight Binding with Machine Learning Potential Model for Magnesium Compounds","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18691","citing_title":"Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24073","citing_title":"Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29584","citing_title":"Geometric Algebra Meets Cartesian Tensors: Higher-Order Equivariance for Interatomic Potentials","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00666","citing_title":"Manifold Diffusion for Structure Generation of Transition Metal Complexes","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30822","citing_title":"Using graph neural networks to predict many-body interactions in amorphous materials","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03232","citing_title":"GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2410.18151","citing_title":"Music102: An $D_{12}$-equivariant transformer for chord progression accompaniment","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2512.25061","citing_title":"Physics-Constrained Self-Energy Warm Starts for Charge-Self-Consistent DFT+DMFT: Application to Iron at Core Conditions","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20440","citing_title":"Exact Symmetry as Algebra: A Machine-Verified Tensor Calculus that Enforces Physical Selection Rules","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14665","citing_title":"Accurate and scalable exchange-correlation with deep learning","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24886","citing_title":"Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks","ref_index":8,"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17129","citing_title":"DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulations","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17219","citing_title":"Vibrational infrared and Raman spectra of the methanol molecule with equivariant neural-network property surfaces","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15073","citing_title":"Fast contracted Clebsch--Gordan tensor products for equivariant graph neural networks","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02824","citing_title":"Disorder-induced chirality in superconductor-ferromagnet heterostructures revealed by neutron scattering and multiscale modeling","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09909","citing_title":"Symmetry-Protected Basin Localization in Variational Quantum Eigensolvers","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08286","citing_title":"Diagnosing Spectral Ceilings in Equivariant Neural Force Fields","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08885","citing_title":"Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12140","citing_title":"XANE(3): An E(3)-Equivariant Graph Neural Network for Accurate Prediction of XANES Spectra from Atomic Structures","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04138","citing_title":"Galactic Amnesia: The Information Washout of the Milky Way Merger History","ref_index":148,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CD52RFJZC4LL55YSMC4TDGFSP","json":"https://pith.science/pith/4CD52RFJZC4LL55YSMC4TDGFSP.json","graph_json":"https://pith.science/api/pith-number/4CD52RFJZC4LL55YSMC4TDGFSP/graph.json","events_json":"https://pith.science/api/pith-number/4CD52RFJZC4LL55YSMC4TDGFSP/events.json","paper":"https://pith.science/paper/4CD52RFJ"},"agent_actions":{"view_html":"https://pith.science/pith/4CD52RFJZC4LL55YSMC4TDGFSP","download_json":"https://pith.science/pith/4CD52RFJZC4LL55YSMC4TDGFSP.json","view_paper":"https://pith.science/paper/4CD52RFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.09453&json=true","fetch_graph":"https://pith.science/api/pith-number/4CD52RFJZC4LL55YSMC4TDGFSP/graph.json","fetch_events":"https://pith.science/api/pith-number/4CD52RFJZC4LL55YSMC4TDGFSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CD52RFJZC4LL55YSMC4TDGFSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CD52RFJZC4LL55YSMC4TDGFSP/action/storage_attestation","attest_author":"https://pith.science/pith/4CD52RFJZC4LL55YSMC4TDGFSP/action/author_attestation","sign_citation":"https://pith.science/pith/4CD52RFJZC4LL55YSMC4TDGFSP/action/citation_signature","submit_replication":"https://pith.science/pith/4CD52RFJZC4LL55YSMC4TDGFSP/action/replication_record"}},"created_at":"2026-07-05T04:41:57.959969+00:00","updated_at":"2026-07-05T04:41:57.959969+00:00"}