{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2GLSJXO7RLRAJWAAMK37QA7LVX","short_pith_number":"pith:2GLSJXO7","schema_version":"1.0","canonical_sha256":"d19724dddf8ae204d80062b7f803ebadd80207df57c3ceb45cdb761b3cc8c64f","source":{"kind":"arxiv","id":"2106.06020","version":1},"attestation_state":"computed","paper":{"title":"Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CG","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Erik Verlinde, Maurice Weiler, Max Welling, Patrick Forr\\'e","submitted_at":"2021-06-10T19:54:19Z","abstract_excerpt":"Motivated by the vast success of deep convolutional networks, there is a great interest in generalizing convolutions to non-Euclidean manifolds. A major complication in comparison to flat spaces is that it is unclear in which alignment a convolution kernel should be applied on a manifold. The underlying reason for this ambiguity is that general manifolds do not come with a canonical choice of reference frames (gauge). Kernels and features therefore have to be expressed relative to arbitrary coordinates. We argue that the particular choice of coordinatization should not affect a network's infer"},"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":"2106.06020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-10T19:54:19Z","cross_cats_sorted":["cs.CG","cs.CV","stat.ML"],"title_canon_sha256":"1102a89a403e6b21b1b2e1d7815ff60dc633adeb0a4b8421e32baf5d3228e097","abstract_canon_sha256":"8877094a42848ce8550d614ece725921aa031557b07f04a3a813965787d5c390"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:25.084840Z","signature_b64":"ASRfYJsuD2JT892JqC3luCjWEy9yr7MnCylHWws2VIcSzGFbGNP2YUCXSmfmMluhmUmj8Jqmy2X3/7wgZtTeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d19724dddf8ae204d80062b7f803ebadd80207df57c3ceb45cdb761b3cc8c64f","last_reissued_at":"2026-07-05T02:48:25.084347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:25.084347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CG","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Erik Verlinde, Maurice Weiler, Max Welling, Patrick Forr\\'e","submitted_at":"2021-06-10T19:54:19Z","abstract_excerpt":"Motivated by the vast success of deep convolutional networks, there is a great interest in generalizing convolutions to non-Euclidean manifolds. A major complication in comparison to flat spaces is that it is unclear in which alignment a convolution kernel should be applied on a manifold. The underlying reason for this ambiguity is that general manifolds do not come with a canonical choice of reference frames (gauge). Kernels and features therefore have to be expressed relative to arbitrary coordinates. We argue that the particular choice of coordinatization should not affect a network's infer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06020","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/2106.06020/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":"2106.06020","created_at":"2026-07-05T02:48:25.084407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06020v1","created_at":"2026-07-05T02:48:25.084407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06020","created_at":"2026-07-05T02:48:25.084407+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GLSJXO7RLRA","created_at":"2026-07-05T02:48:25.084407+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GLSJXO7RLRAJWAA","created_at":"2026-07-05T02:48:25.084407+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GLSJXO7","created_at":"2026-07-05T02:48:25.084407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13834","citing_title":"Topology-Preserving Neural Operator Learning via Hodge Decomposition","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15368","citing_title":"Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24886","citing_title":"Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27420","citing_title":"Towards a Multi-Embodied Grasping Agent","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13834","citing_title":"Topology-Preserving Neural Operator Learning via Hodge Decomposition","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GLSJXO7RLRAJWAAMK37QA7LVX","json":"https://pith.science/pith/2GLSJXO7RLRAJWAAMK37QA7LVX.json","graph_json":"https://pith.science/api/pith-number/2GLSJXO7RLRAJWAAMK37QA7LVX/graph.json","events_json":"https://pith.science/api/pith-number/2GLSJXO7RLRAJWAAMK37QA7LVX/events.json","paper":"https://pith.science/paper/2GLSJXO7"},"agent_actions":{"view_html":"https://pith.science/pith/2GLSJXO7RLRAJWAAMK37QA7LVX","download_json":"https://pith.science/pith/2GLSJXO7RLRAJWAAMK37QA7LVX.json","view_paper":"https://pith.science/paper/2GLSJXO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06020&json=true","fetch_graph":"https://pith.science/api/pith-number/2GLSJXO7RLRAJWAAMK37QA7LVX/graph.json","fetch_events":"https://pith.science/api/pith-number/2GLSJXO7RLRAJWAAMK37QA7LVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GLSJXO7RLRAJWAAMK37QA7LVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GLSJXO7RLRAJWAAMK37QA7LVX/action/storage_attestation","attest_author":"https://pith.science/pith/2GLSJXO7RLRAJWAAMK37QA7LVX/action/author_attestation","sign_citation":"https://pith.science/pith/2GLSJXO7RLRAJWAAMK37QA7LVX/action/citation_signature","submit_replication":"https://pith.science/pith/2GLSJXO7RLRAJWAAMK37QA7LVX/action/replication_record"}},"created_at":"2026-07-05T02:48:25.084407+00:00","updated_at":"2026-07-05T02:48:25.084407+00:00"}