{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FQJLDCATS7YXE74D3NNMDWD2SJ","short_pith_number":"pith:FQJLDCAT","schema_version":"1.0","canonical_sha256":"2c12b1881397f1727f83db5ac1d87a9240423dfd6d5651b2e2ac0543f1a5f324","source":{"kind":"arxiv","id":"2004.02658","version":1},"attestation_state":"computed","paper":{"title":"Geometrically Principled Connections in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mehdi Bahri, Michael M. Bronstein, Shunwang Gong, Stefanos Zafeiriou","submitted_at":"2020-04-06T13:25:46Z","abstract_excerpt":"Graph convolution operators bring the advantages of deep learning to a variety of graph and mesh processing tasks previously deemed out of reach. With their continued success comes the desire to design more powerful architectures, often by adapting existing deep learning techniques to non-Euclidean data. In this paper, we argue geometry should remain the primary driving force behind innovation in the emerging field of geometric deep learning. We relate graph neural networks to widely successful computer graphics and data approximation models: radial basis functions (RBFs). We conjecture that, "},"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":"2004.02658","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-06T13:25:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c4a6ccd216e32f792c5c59bc87e5dbf51ec9dbb2e8c2ca842e38bf399746e2ac","abstract_canon_sha256":"f32f285ecd14d29353a767b7a455a604a7c068fd420c3c2362aaa7b2f9917aba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:01.391218Z","signature_b64":"A9hxfA4G5tmYp4rnlMWL24Bz0YE2p7aPCqw32fro65XE9GmBfKGtr6Tl1iES4i3mf2XufTIolJWSjJ7aTqNTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c12b1881397f1727f83db5ac1d87a9240423dfd6d5651b2e2ac0543f1a5f324","last_reissued_at":"2026-07-05T00:53:01.390825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:01.390825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometrically Principled Connections in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mehdi Bahri, Michael M. Bronstein, Shunwang Gong, Stefanos Zafeiriou","submitted_at":"2020-04-06T13:25:46Z","abstract_excerpt":"Graph convolution operators bring the advantages of deep learning to a variety of graph and mesh processing tasks previously deemed out of reach. With their continued success comes the desire to design more powerful architectures, often by adapting existing deep learning techniques to non-Euclidean data. In this paper, we argue geometry should remain the primary driving force behind innovation in the emerging field of geometric deep learning. We relate graph neural networks to widely successful computer graphics and data approximation models: radial basis functions (RBFs). We conjecture that, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02658","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/2004.02658/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":"2004.02658","created_at":"2026-07-05T00:53:01.390887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02658v1","created_at":"2026-07-05T00:53:01.390887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02658","created_at":"2026-07-05T00:53:01.390887+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQJLDCATS7YX","created_at":"2026-07-05T00:53:01.390887+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQJLDCATS7YXE74D","created_at":"2026-07-05T00:53:01.390887+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQJLDCAT","created_at":"2026-07-05T00:53:01.390887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQJLDCATS7YXE74D3NNMDWD2SJ","json":"https://pith.science/pith/FQJLDCATS7YXE74D3NNMDWD2SJ.json","graph_json":"https://pith.science/api/pith-number/FQJLDCATS7YXE74D3NNMDWD2SJ/graph.json","events_json":"https://pith.science/api/pith-number/FQJLDCATS7YXE74D3NNMDWD2SJ/events.json","paper":"https://pith.science/paper/FQJLDCAT"},"agent_actions":{"view_html":"https://pith.science/pith/FQJLDCATS7YXE74D3NNMDWD2SJ","download_json":"https://pith.science/pith/FQJLDCATS7YXE74D3NNMDWD2SJ.json","view_paper":"https://pith.science/paper/FQJLDCAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02658&json=true","fetch_graph":"https://pith.science/api/pith-number/FQJLDCATS7YXE74D3NNMDWD2SJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FQJLDCATS7YXE74D3NNMDWD2SJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQJLDCATS7YXE74D3NNMDWD2SJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQJLDCATS7YXE74D3NNMDWD2SJ/action/storage_attestation","attest_author":"https://pith.science/pith/FQJLDCATS7YXE74D3NNMDWD2SJ/action/author_attestation","sign_citation":"https://pith.science/pith/FQJLDCATS7YXE74D3NNMDWD2SJ/action/citation_signature","submit_replication":"https://pith.science/pith/FQJLDCATS7YXE74D3NNMDWD2SJ/action/replication_record"}},"created_at":"2026-07-05T00:53:01.390887+00:00","updated_at":"2026-07-05T00:53:01.390887+00:00"}