{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HDZOPA5CUFFYFUTFNTTNUXNXYE","short_pith_number":"pith:HDZOPA5C","schema_version":"1.0","canonical_sha256":"38f2e783a2a14b82d2656ce6da5db7c13f82ac8bfc8cc21313d749fff7ca72cd","source":{"kind":"arxiv","id":"2002.05287","version":2},"attestation_state":"computed","paper":{"title":"Geom-GCN: Geometric Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingzhe Wei, Bo Yang, Hongbin Pei, Kevin Chen-Chuan Chang, Yu Lei","submitted_at":"2020-02-13T00:03:09Z","abstract_excerpt":"Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs. Few studies have noticed the weaknesses from different perspectives. From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for"},"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":"2002.05287","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-13T00:03:09Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3793cbbbb6a875a5a239ab1514823718e1fadbd505eddcdd90fb03f492182995","abstract_canon_sha256":"3cdc432510efd19daeffe201c9d456ded65880e668426c16566249b35b3e176b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:46.940472Z","signature_b64":"3inPFTTFHoDrhW/PKOpIYz/CKjGkV7eK742rXXD75CDCvT2f4CdWwTPSZ3WfI3a7bZu7g2konkcCg6cyZbnWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38f2e783a2a14b82d2656ce6da5db7c13f82ac8bfc8cc21313d749fff7ca72cd","last_reissued_at":"2026-07-05T00:40:46.939992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:46.939992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geom-GCN: Geometric Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingzhe Wei, Bo Yang, Hongbin Pei, Kevin Chen-Chuan Chang, Yu Lei","submitted_at":"2020-02-13T00:03:09Z","abstract_excerpt":"Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs. Few studies have noticed the weaknesses from different perspectives. From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05287","kind":"arxiv","version":2},"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/2002.05287/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":"2002.05287","created_at":"2026-07-05T00:40:46.940057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05287v2","created_at":"2026-07-05T00:40:46.940057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05287","created_at":"2026-07-05T00:40:46.940057+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDZOPA5CUFFY","created_at":"2026-07-05T00:40:46.940057+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDZOPA5CUFFYFUTF","created_at":"2026-07-05T00:40:46.940057+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDZOPA5C","created_at":"2026-07-05T00:40:46.940057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10284","citing_title":"Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19405","citing_title":"A complete discussion on fully reconfigurable, digital, scalable, graph and sparsity-aware near-memory accelerator for graph neural networks","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21247","citing_title":"Graph Navier Stokes Networks","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05311","citing_title":"PLACE: Prompt Learning for Attributed Community Search in Large Graphs","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20248","citing_title":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21247","citing_title":"Graph Navier Stokes Networks","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19405","citing_title":"A complete discussion on fully reconfigurable, digital, scalable, graph and sparsity-aware near-memory accelerator for graph neural networks","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09457","citing_title":"RAwR: Role-Aware Rewiring via Approximate Equitable Partition","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19186","citing_title":"Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15699","citing_title":"Frequency-Corrupt Based Graph Self-Supervised Learning","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDZOPA5CUFFYFUTFNTTNUXNXYE","json":"https://pith.science/pith/HDZOPA5CUFFYFUTFNTTNUXNXYE.json","graph_json":"https://pith.science/api/pith-number/HDZOPA5CUFFYFUTFNTTNUXNXYE/graph.json","events_json":"https://pith.science/api/pith-number/HDZOPA5CUFFYFUTFNTTNUXNXYE/events.json","paper":"https://pith.science/paper/HDZOPA5C"},"agent_actions":{"view_html":"https://pith.science/pith/HDZOPA5CUFFYFUTFNTTNUXNXYE","download_json":"https://pith.science/pith/HDZOPA5CUFFYFUTFNTTNUXNXYE.json","view_paper":"https://pith.science/paper/HDZOPA5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05287&json=true","fetch_graph":"https://pith.science/api/pith-number/HDZOPA5CUFFYFUTFNTTNUXNXYE/graph.json","fetch_events":"https://pith.science/api/pith-number/HDZOPA5CUFFYFUTFNTTNUXNXYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDZOPA5CUFFYFUTFNTTNUXNXYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDZOPA5CUFFYFUTFNTTNUXNXYE/action/storage_attestation","attest_author":"https://pith.science/pith/HDZOPA5CUFFYFUTFNTTNUXNXYE/action/author_attestation","sign_citation":"https://pith.science/pith/HDZOPA5CUFFYFUTFNTTNUXNXYE/action/citation_signature","submit_replication":"https://pith.science/pith/HDZOPA5CUFFYFUTFNTTNUXNXYE/action/replication_record"}},"created_at":"2026-07-05T00:40:46.940057+00:00","updated_at":"2026-07-05T00:40:46.940057+00:00"}