{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GK7HWJYOYKO4FSHOBAZ3TMSI2E","short_pith_number":"pith:GK7HWJYO","schema_version":"1.0","canonical_sha256":"32be7b270ec29dc2c8ee0833b9b248d133fefadaa9645a7588a3f2ac7d0d7b00","source":{"kind":"arxiv","id":"2206.04176","version":3},"attestation_state":"computed","paper":{"title":"VN-Transformer: Rotation-Equivariant Attention for Vector Neurons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ben Sapp, Carlton Downey, Nigamaa Nayakanti, Rami Al-Rfou, Serge Assaad","submitted_at":"2022-06-08T21:48:47Z","abstract_excerpt":"Rotation equivariance is a desirable property in many practical applications such as motion forecasting and 3D perception, where it can offer benefits like sample efficiency, better generalization, and robustness to input perturbations. Vector Neurons (VN) is a recently developed framework offering a simple yet effective approach for deriving rotation-equivariant analogs of standard machine learning operations by extending one-dimensional scalar neurons to three-dimensional \"vector neurons.\" We introduce a novel \"VN-Transformer\" architecture to address several shortcomings of the current VN mo"},"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":"2206.04176","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-08T21:48:47Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"eb98e9a236cfa2a30878012c426055320cfb2627187260b1f90da74beceed813","abstract_canon_sha256":"18274bd6f60feba524179fefe11c0c362f25f5e47076a9ddb2db780a2ce5c990"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:44.117788Z","signature_b64":"65fHZaBaAuWKJPu8EwYn8bdQ1lcAL703/TKDeXJ5/IzVutVrs4KOasvsikOEP2LLB8GL/CJwNx+lopXsjaiCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32be7b270ec29dc2c8ee0833b9b248d133fefadaa9645a7588a3f2ac7d0d7b00","last_reissued_at":"2026-07-05T05:35:44.117382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:44.117382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VN-Transformer: Rotation-Equivariant Attention for Vector Neurons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ben Sapp, Carlton Downey, Nigamaa Nayakanti, Rami Al-Rfou, Serge Assaad","submitted_at":"2022-06-08T21:48:47Z","abstract_excerpt":"Rotation equivariance is a desirable property in many practical applications such as motion forecasting and 3D perception, where it can offer benefits like sample efficiency, better generalization, and robustness to input perturbations. Vector Neurons (VN) is a recently developed framework offering a simple yet effective approach for deriving rotation-equivariant analogs of standard machine learning operations by extending one-dimensional scalar neurons to three-dimensional \"vector neurons.\" We introduce a novel \"VN-Transformer\" architecture to address several shortcomings of the current VN mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04176","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.04176/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":"2206.04176","created_at":"2026-07-05T05:35:44.117437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04176v3","created_at":"2026-07-05T05:35:44.117437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04176","created_at":"2026-07-05T05:35:44.117437+00:00"},{"alias_kind":"pith_short_12","alias_value":"GK7HWJYOYKO4","created_at":"2026-07-05T05:35:44.117437+00:00"},{"alias_kind":"pith_short_16","alias_value":"GK7HWJYOYKO4FSHO","created_at":"2026-07-05T05:35:44.117437+00:00"},{"alias_kind":"pith_short_8","alias_value":"GK7HWJYO","created_at":"2026-07-05T05:35:44.117437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25318","citing_title":"REViT: Roto-reflection Equivariant Convolutional Vision Transformer","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":2,"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":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GK7HWJYOYKO4FSHOBAZ3TMSI2E","json":"https://pith.science/pith/GK7HWJYOYKO4FSHOBAZ3TMSI2E.json","graph_json":"https://pith.science/api/pith-number/GK7HWJYOYKO4FSHOBAZ3TMSI2E/graph.json","events_json":"https://pith.science/api/pith-number/GK7HWJYOYKO4FSHOBAZ3TMSI2E/events.json","paper":"https://pith.science/paper/GK7HWJYO"},"agent_actions":{"view_html":"https://pith.science/pith/GK7HWJYOYKO4FSHOBAZ3TMSI2E","download_json":"https://pith.science/pith/GK7HWJYOYKO4FSHOBAZ3TMSI2E.json","view_paper":"https://pith.science/paper/GK7HWJYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04176&json=true","fetch_graph":"https://pith.science/api/pith-number/GK7HWJYOYKO4FSHOBAZ3TMSI2E/graph.json","fetch_events":"https://pith.science/api/pith-number/GK7HWJYOYKO4FSHOBAZ3TMSI2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GK7HWJYOYKO4FSHOBAZ3TMSI2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GK7HWJYOYKO4FSHOBAZ3TMSI2E/action/storage_attestation","attest_author":"https://pith.science/pith/GK7HWJYOYKO4FSHOBAZ3TMSI2E/action/author_attestation","sign_citation":"https://pith.science/pith/GK7HWJYOYKO4FSHOBAZ3TMSI2E/action/citation_signature","submit_replication":"https://pith.science/pith/GK7HWJYOYKO4FSHOBAZ3TMSI2E/action/replication_record"}},"created_at":"2026-07-05T05:35:44.117437+00:00","updated_at":"2026-07-05T05:35:44.117437+00:00"}