{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Q6PYZ5ECQJDC2BV54KLKSKWCEC","short_pith_number":"pith:Q6PYZ5EC","schema_version":"1.0","canonical_sha256":"879f8cf48282462d06bde296a92ac220a22ed0c8aa3b642d02bcc0b15ad587c8","source":{"kind":"arxiv","id":"1810.02303","version":1},"attestation_state":"computed","paper":{"title":"Multi-directional Geodesic Neural Networks via Equivariant Convolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CG","cs.LG"],"primary_cat":"cs.GR","authors_text":"Adrien Poulenard, Maks Ovsjanikov","submitted_at":"2018-10-01T18:03:24Z","abstract_excerpt":"We propose a novel approach for performing convolution of signals on curved surfaces and show its utility in a variety of geometric deep learning applications. Key to our construction is the notion of directional functions defined on the surface, which extend the classic real-valued signals and which can be naturally convolved with with real-valued template functions. As a result, rather than trying to fix a canonical orientation or only keeping the maximal response across all alignments of a 2D template at every point of the surface, as done in previous works, we show how information across a"},"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":"1810.02303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2018-10-01T18:03:24Z","cross_cats_sorted":["cs.CG","cs.LG"],"title_canon_sha256":"15170162099d54adebd5ceef2617f4c52d1850a6159f430cb055586b0149bc95","abstract_canon_sha256":"d9bbeb4eecef82efcf0f9b5402de6d6578f833258bd198314917c68a43d76d67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:05.674034Z","signature_b64":"Pg+2RpLHFzF294GbGqILgKNcEsK6o87gL7kBh7a9NleUlEM8pnHScS6ARpV+VuuJ9qVX4PqPq3kVeoASvSrOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"879f8cf48282462d06bde296a92ac220a22ed0c8aa3b642d02bcc0b15ad587c8","last_reissued_at":"2026-05-18T00:04:05.673261Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:05.673261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-directional Geodesic Neural Networks via Equivariant Convolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CG","cs.LG"],"primary_cat":"cs.GR","authors_text":"Adrien Poulenard, Maks Ovsjanikov","submitted_at":"2018-10-01T18:03:24Z","abstract_excerpt":"We propose a novel approach for performing convolution of signals on curved surfaces and show its utility in a variety of geometric deep learning applications. Key to our construction is the notion of directional functions defined on the surface, which extend the classic real-valued signals and which can be naturally convolved with with real-valued template functions. As a result, rather than trying to fix a canonical orientation or only keeping the maximal response across all alignments of a 2D template at every point of the surface, as done in previous works, we show how information across a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02303","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":""},"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":"1810.02303","created_at":"2026-05-18T00:04:05.673407+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02303v1","created_at":"2026-05-18T00:04:05.673407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02303","created_at":"2026-05-18T00:04:05.673407+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6PYZ5ECQJDC","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6PYZ5ECQJDC2BV5","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6PYZ5EC","created_at":"2026-05-18T12:32:46.962924+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/Q6PYZ5ECQJDC2BV54KLKSKWCEC","json":"https://pith.science/pith/Q6PYZ5ECQJDC2BV54KLKSKWCEC.json","graph_json":"https://pith.science/api/pith-number/Q6PYZ5ECQJDC2BV54KLKSKWCEC/graph.json","events_json":"https://pith.science/api/pith-number/Q6PYZ5ECQJDC2BV54KLKSKWCEC/events.json","paper":"https://pith.science/paper/Q6PYZ5EC"},"agent_actions":{"view_html":"https://pith.science/pith/Q6PYZ5ECQJDC2BV54KLKSKWCEC","download_json":"https://pith.science/pith/Q6PYZ5ECQJDC2BV54KLKSKWCEC.json","view_paper":"https://pith.science/paper/Q6PYZ5EC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02303&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6PYZ5ECQJDC2BV54KLKSKWCEC/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6PYZ5ECQJDC2BV54KLKSKWCEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6PYZ5ECQJDC2BV54KLKSKWCEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6PYZ5ECQJDC2BV54KLKSKWCEC/action/storage_attestation","attest_author":"https://pith.science/pith/Q6PYZ5ECQJDC2BV54KLKSKWCEC/action/author_attestation","sign_citation":"https://pith.science/pith/Q6PYZ5ECQJDC2BV54KLKSKWCEC/action/citation_signature","submit_replication":"https://pith.science/pith/Q6PYZ5ECQJDC2BV54KLKSKWCEC/action/replication_record"}},"created_at":"2026-05-18T00:04:05.673407+00:00","updated_at":"2026-05-18T00:04:05.673407+00:00"}