{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HM7CVLO475B2FDHQ6IRS3K3AGK","short_pith_number":"pith:HM7CVLO4","schema_version":"1.0","canonical_sha256":"3b3e2aaddcff43a28cf0f2232dab6032be55a3ff88aa5bda6b6bfb3015999576","source":{"kind":"arxiv","id":"1802.08219","version":3},"attestation_state":"computed","paper":{"title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Kai Kohlhoff, Li Li, Lusann Yang, Nathaniel Thomas, Patrick Riley, Steven Kearnes, Tess Smidt","submitted_at":"2018-02-22T18:17:31Z","abstract_excerpt":"We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer. 3D rotation equivariance removes the need for data augmentation to identify features in arbitrary orientations. Our network uses filters built from spherical harmonics; due to the mathematical consequences of this filter choice, each layer accepts as input (and guarantees as output) scalars, vectors, and higher-order tensors, in the geometric sense of these terms. We demonstrate the capabilities of tensor field networks with tasks in geometry, physi"},"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":"1802.08219","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-22T18:17:31Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE"],"title_canon_sha256":"206d832d98b2279ff802318e25702d9379b934be8f6265a9fcbdc7a2bdda6864","abstract_canon_sha256":"1619bcd41fcba38eb72b0c4007f735f18e8936bd7ad917b59d42cf0e4e980856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:36.583816Z","signature_b64":"JjaIjsMxOzS6nff2T2K3+T5o/BMz+77Vhlo7C0vZX0x1oQuGkUIOD2NGnLvzQswpurqVYtE8wzyZqMOYlQmRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b3e2aaddcff43a28cf0f2232dab6032be55a3ff88aa5bda6b6bfb3015999576","last_reissued_at":"2026-05-18T00:15:36.583101Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:36.583101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Kai Kohlhoff, Li Li, Lusann Yang, Nathaniel Thomas, Patrick Riley, Steven Kearnes, Tess Smidt","submitted_at":"2018-02-22T18:17:31Z","abstract_excerpt":"We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer. 3D rotation equivariance removes the need for data augmentation to identify features in arbitrary orientations. Our network uses filters built from spherical harmonics; due to the mathematical consequences of this filter choice, each layer accepts as input (and guarantees as output) scalars, vectors, and higher-order tensors, in the geometric sense of these terms. We demonstrate the capabilities of tensor field networks with tasks in geometry, physi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08219","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.08219","created_at":"2026-05-18T00:15:36.583194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08219v3","created_at":"2026-05-18T00:15:36.583194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08219","created_at":"2026-05-18T00:15:36.583194+00:00"},{"alias_kind":"pith_short_12","alias_value":"HM7CVLO475B2","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HM7CVLO475B2FDHQ","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HM7CVLO4","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":54,"internal_anchor_count":42,"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":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25075","citing_title":"Solver Exactness, Learned Flexibility: Equivariant Boundary-Correction Operators for Stokes Flow","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25006","citing_title":"Scalable Peptide Design via Memory-Efficient Equivariant Transformer","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25006","citing_title":"Scalable Peptide Design via Memory-Efficient Equivariant Transformer","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19928","citing_title":"SWAP: Symmetric Equivariant World-Model for Agile Robot Parkour","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20547","citing_title":"The Token Is a Group Element: On Lie-Algebra Attention over Matrix Lie Groups","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18691","citing_title":"Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01408","citing_title":"Spin-Weighted Spherical Harmonics Enable Complete and Scalable $\\mathrm{E}(3)$-Equivariant Networks","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11685","citing_title":"DSpinGNN: A Physics-Informed Equivariant Graph Neural Network for Dynamic Magnetic Exchange Prediction in Strain-Deformed Monolayer CrI$_3$","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09432","citing_title":"Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07327","citing_title":"Six Open Questions in Machine-Learned Interatomic Potential Foundation Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04468","citing_title":"ParetoPilot: Zero-Surrogate Offline Multi-Objective Optimization via Infer-Perturb-Guide Diffusion","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02419","citing_title":"DPA4: Pushing the Accuracy-Cost Frontier of Interatomic Potentials with EMFA SO(2) Convolution","ref_index":190,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01090","citing_title":"Measuring the Symmetry--Data Exchange Rate","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27412","citing_title":"From Scene-Centric to Observer-Centric: Modeling Observer-Aware Relations for 3D Scene Graph Generation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15008","citing_title":"Majorana Constellations: A Geometric Lens on Multipartite Entanglement and Geometric Phases","ref_index":100,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30778","citing_title":"ReactionAtlas: Ab origine exploration of chemical reaction networks with machine learning","ref_index":89,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17929","citing_title":"TacSE3: Equivariant SE(3) Motion Estimation from Low-Texture Visuotactile Images for In-Gripper Tracking and Compensation","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24013","citing_title":"UniField: RBF-Guided Electron Density Fusion for Enhanced Molecular Representations","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24073","citing_title":"Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24578","citing_title":"World Models as Group Actions","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2606.29584","citing_title":"Geometric Algebra Meets Cartesian Tensors: Higher-Order Equivariance for Interatomic Potentials","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22182","citing_title":"Dual-Stream EEG Decoding for 3D Visual Perception","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23214","citing_title":"Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"1906.10033","citing_title":"Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctions","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HM7CVLO475B2FDHQ6IRS3K3AGK","json":"https://pith.science/pith/HM7CVLO475B2FDHQ6IRS3K3AGK.json","graph_json":"https://pith.science/api/pith-number/HM7CVLO475B2FDHQ6IRS3K3AGK/graph.json","events_json":"https://pith.science/api/pith-number/HM7CVLO475B2FDHQ6IRS3K3AGK/events.json","paper":"https://pith.science/paper/HM7CVLO4"},"agent_actions":{"view_html":"https://pith.science/pith/HM7CVLO475B2FDHQ6IRS3K3AGK","download_json":"https://pith.science/pith/HM7CVLO475B2FDHQ6IRS3K3AGK.json","view_paper":"https://pith.science/paper/HM7CVLO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08219&json=true","fetch_graph":"https://pith.science/api/pith-number/HM7CVLO475B2FDHQ6IRS3K3AGK/graph.json","fetch_events":"https://pith.science/api/pith-number/HM7CVLO475B2FDHQ6IRS3K3AGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HM7CVLO475B2FDHQ6IRS3K3AGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HM7CVLO475B2FDHQ6IRS3K3AGK/action/storage_attestation","attest_author":"https://pith.science/pith/HM7CVLO475B2FDHQ6IRS3K3AGK/action/author_attestation","sign_citation":"https://pith.science/pith/HM7CVLO475B2FDHQ6IRS3K3AGK/action/citation_signature","submit_replication":"https://pith.science/pith/HM7CVLO475B2FDHQ6IRS3K3AGK/action/replication_record"}},"created_at":"2026-05-18T00:15:36.583194+00:00","updated_at":"2026-05-18T00:15:36.583194+00:00"}