{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VUG4UZF3TXA3VKMMZ7OD2BAOVJ","short_pith_number":"pith:VUG4UZF3","schema_version":"1.0","canonical_sha256":"ad0dca64bb9dc1baa98ccfdc3d040eaa59f9152eb23b52e9d4269aaaf0c9a6e0","source":{"kind":"arxiv","id":"2105.13926","version":1},"attestation_state":"computed","paper":{"title":"Geometric Deep Learning and Equivariant Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","hep-th"],"primary_cat":"cs.LG","authors_text":"Christoffer Petersson, Daniel Persson, Fredrik Ohlsson, Hampus Linander, Jan E. Gerken, Jimmy Aronsson, Oscar Carlsson","submitted_at":"2021-05-28T15:41:52Z","abstract_excerpt":"We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional neural networks on arbitrary manifolds $\\mathcal{M}$ using principal bundles with structure group $K$ and equivariant maps between sections of associated vector bundles. We also discuss group equivariant neural networks for homogeneous spaces $\\mathcal{M}=G/K$, which are instead equivariant with respect to the global symmetry $G$ on $\\mathcal{M}$. Group equivariant layers can be interpreted as intertwiners between ind"},"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":"2105.13926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T15:41:52Z","cross_cats_sorted":["cs.CV","hep-th"],"title_canon_sha256":"0ed1397fc9c037759a493ea08b269bab3ab07f0304c6da652fc718b11a317655","abstract_canon_sha256":"2201fd98dcd76c8cbcefdd2f287a691d617debacadb27398a406db6aaeca4c78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:12.645280Z","signature_b64":"BOlMJg3A9q2swp317N1JQ6eYOe7YReCpmB/L8UrOoi0pivoR2WLwqNSehGxyImMs+wvDAh6ApDM8V5oI3qL4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad0dca64bb9dc1baa98ccfdc3d040eaa59f9152eb23b52e9d4269aaaf0c9a6e0","last_reissued_at":"2026-07-05T02:44:12.644881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:12.644881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometric Deep Learning and Equivariant Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","hep-th"],"primary_cat":"cs.LG","authors_text":"Christoffer Petersson, Daniel Persson, Fredrik Ohlsson, Hampus Linander, Jan E. Gerken, Jimmy Aronsson, Oscar Carlsson","submitted_at":"2021-05-28T15:41:52Z","abstract_excerpt":"We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional neural networks on arbitrary manifolds $\\mathcal{M}$ using principal bundles with structure group $K$ and equivariant maps between sections of associated vector bundles. We also discuss group equivariant neural networks for homogeneous spaces $\\mathcal{M}=G/K$, which are instead equivariant with respect to the global symmetry $G$ on $\\mathcal{M}$. Group equivariant layers can be interpreted as intertwiners between ind"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13926","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/2105.13926/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":"2105.13926","created_at":"2026-07-05T02:44:12.644942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.13926v1","created_at":"2026-07-05T02:44:12.644942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13926","created_at":"2026-07-05T02:44:12.644942+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUG4UZF3TXA3","created_at":"2026-07-05T02:44:12.644942+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUG4UZF3TXA3VKMM","created_at":"2026-07-05T02:44:12.644942+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUG4UZF3","created_at":"2026-07-05T02:44:12.644942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12493","citing_title":"Symmetry-preserving neural networks in lattice field theories","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VUG4UZF3TXA3VKMMZ7OD2BAOVJ","json":"https://pith.science/pith/VUG4UZF3TXA3VKMMZ7OD2BAOVJ.json","graph_json":"https://pith.science/api/pith-number/VUG4UZF3TXA3VKMMZ7OD2BAOVJ/graph.json","events_json":"https://pith.science/api/pith-number/VUG4UZF3TXA3VKMMZ7OD2BAOVJ/events.json","paper":"https://pith.science/paper/VUG4UZF3"},"agent_actions":{"view_html":"https://pith.science/pith/VUG4UZF3TXA3VKMMZ7OD2BAOVJ","download_json":"https://pith.science/pith/VUG4UZF3TXA3VKMMZ7OD2BAOVJ.json","view_paper":"https://pith.science/paper/VUG4UZF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.13926&json=true","fetch_graph":"https://pith.science/api/pith-number/VUG4UZF3TXA3VKMMZ7OD2BAOVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VUG4UZF3TXA3VKMMZ7OD2BAOVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUG4UZF3TXA3VKMMZ7OD2BAOVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUG4UZF3TXA3VKMMZ7OD2BAOVJ/action/storage_attestation","attest_author":"https://pith.science/pith/VUG4UZF3TXA3VKMMZ7OD2BAOVJ/action/author_attestation","sign_citation":"https://pith.science/pith/VUG4UZF3TXA3VKMMZ7OD2BAOVJ/action/citation_signature","submit_replication":"https://pith.science/pith/VUG4UZF3TXA3VKMMZ7OD2BAOVJ/action/replication_record"}},"created_at":"2026-07-05T02:44:12.644942+00:00","updated_at":"2026-07-05T02:44:12.644942+00:00"}