{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ITPJVU3SLDBE5KRQKHAOWQYKPS","short_pith_number":"pith:ITPJVU3S","schema_version":"1.0","canonical_sha256":"44de9ad37258c24eaa3051c0eb430a7c90ee0a72f1a8686cb1a7573d8e3f42c4","source":{"kind":"arxiv","id":"2104.06942","version":1},"attestation_state":"computed","paper":{"title":"A Hyperbolic-to-Hyperbolic Graph Convolutional Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jindou Dai, Yunde Jia, Yuwei Wu, Zhi Gao","submitted_at":"2021-04-14T16:09:27Z","abstract_excerpt":"Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to tangent spaces to realize graph convolution on hyperbolic manifolds, which is inferior because tangent space is only a local approximation of a manifold. In this paper, we propose a hyperbolic-to-hyperbolic graph convolutional network (H2H-GCN) that directly works on hyperbolic manifolds. Specifically, we developed a manifold-preserving graph convolution that consists of a hyperbolic feature transformation and a hyperbolic ne"},"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":"2104.06942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-14T16:09:27Z","cross_cats_sorted":[],"title_canon_sha256":"cd25934622b2539c54d633bf14932221372b7175f24b47f9e78e67ea2a96c560","abstract_canon_sha256":"d16cc8a9ebca4e1179d009f25f86e982648b960565463e13218c50b55d00f2df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:11.262379Z","signature_b64":"y8CSKo0QPnzfdCtygxqK7n4uhnMKd1ZXOzZEAGHqNrmL659aIXXoJut2WyJQszGEulHgAmCoDkbeA+ntswSRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44de9ad37258c24eaa3051c0eb430a7c90ee0a72f1a8686cb1a7573d8e3f42c4","last_reissued_at":"2026-07-05T02:32:11.261926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:11.261926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hyperbolic-to-Hyperbolic Graph Convolutional Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jindou Dai, Yunde Jia, Yuwei Wu, Zhi Gao","submitted_at":"2021-04-14T16:09:27Z","abstract_excerpt":"Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to tangent spaces to realize graph convolution on hyperbolic manifolds, which is inferior because tangent space is only a local approximation of a manifold. In this paper, we propose a hyperbolic-to-hyperbolic graph convolutional network (H2H-GCN) that directly works on hyperbolic manifolds. Specifically, we developed a manifold-preserving graph convolution that consists of a hyperbolic feature transformation and a hyperbolic ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06942","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/2104.06942/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":"2104.06942","created_at":"2026-07-05T02:32:11.261981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06942v1","created_at":"2026-07-05T02:32:11.261981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06942","created_at":"2026-07-05T02:32:11.261981+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITPJVU3SLDBE","created_at":"2026-07-05T02:32:11.261981+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITPJVU3SLDBE5KRQ","created_at":"2026-07-05T02:32:11.261981+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITPJVU3S","created_at":"2026-07-05T02:32:11.261981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17787","citing_title":"Hyperbolic Deep Learning for Foundation Models: A Survey","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ITPJVU3SLDBE5KRQKHAOWQYKPS","json":"https://pith.science/pith/ITPJVU3SLDBE5KRQKHAOWQYKPS.json","graph_json":"https://pith.science/api/pith-number/ITPJVU3SLDBE5KRQKHAOWQYKPS/graph.json","events_json":"https://pith.science/api/pith-number/ITPJVU3SLDBE5KRQKHAOWQYKPS/events.json","paper":"https://pith.science/paper/ITPJVU3S"},"agent_actions":{"view_html":"https://pith.science/pith/ITPJVU3SLDBE5KRQKHAOWQYKPS","download_json":"https://pith.science/pith/ITPJVU3SLDBE5KRQKHAOWQYKPS.json","view_paper":"https://pith.science/paper/ITPJVU3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06942&json=true","fetch_graph":"https://pith.science/api/pith-number/ITPJVU3SLDBE5KRQKHAOWQYKPS/graph.json","fetch_events":"https://pith.science/api/pith-number/ITPJVU3SLDBE5KRQKHAOWQYKPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITPJVU3SLDBE5KRQKHAOWQYKPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITPJVU3SLDBE5KRQKHAOWQYKPS/action/storage_attestation","attest_author":"https://pith.science/pith/ITPJVU3SLDBE5KRQKHAOWQYKPS/action/author_attestation","sign_citation":"https://pith.science/pith/ITPJVU3SLDBE5KRQKHAOWQYKPS/action/citation_signature","submit_replication":"https://pith.science/pith/ITPJVU3SLDBE5KRQKHAOWQYKPS/action/replication_record"}},"created_at":"2026-07-05T02:32:11.261981+00:00","updated_at":"2026-07-05T02:32:11.261981+00:00"}