{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:INCKBX2DT4LOGQS5WJMJTD5XK5","short_pith_number":"pith:INCKBX2D","schema_version":"1.0","canonical_sha256":"4344a0df439f16e3425db258998fb75763d0cd282e5ee4540be6260a930d61a9","source":{"kind":"arxiv","id":"2012.11147","version":1},"attestation_state":"computed","paper":{"title":"Hop-Hop Relation-aware Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haiping Lu, Li Zhang, Yan Ge","submitted_at":"2020-12-21T06:58:38Z","abstract_excerpt":"Graph Neural Networks (GNNs) are widely used in graph representation learning. However, most GNN methods are designed for either homogeneous or heterogeneous graphs. In this paper, we propose a new model, Hop-Hop Relation-aware Graph Neural Network (HHR-GNN), to unify representation learning for these two types of graphs. HHR-GNN learns a personalized receptive field for each node by leveraging knowledge graph embedding to learn relation scores between the central node's representations at different hops. In neighborhood aggregation, our model simultaneously allows for hop-aware projection and"},"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":"2012.11147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-21T06:58:38Z","cross_cats_sorted":[],"title_canon_sha256":"35bfdc8d8e87dc0aa3d6ac61749dd5d0bc036e93cab1509dbd4c5a8c6aca2e93","abstract_canon_sha256":"eded859e91c5cb51251bc1b8457958864ef740f546546a70a148b42129b4a4ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:59.071737Z","signature_b64":"236T8N3K2e+UdWU+EfzogzEL6vi9VfJBH1cPkvM07KhanwAs9MRC+CxhIOudoj38BAShEHO3qqDefgaoSRozDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4344a0df439f16e3425db258998fb75763d0cd282e5ee4540be6260a930d61a9","last_reissued_at":"2026-07-05T02:00:59.071361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:59.071361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hop-Hop Relation-aware Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haiping Lu, Li Zhang, Yan Ge","submitted_at":"2020-12-21T06:58:38Z","abstract_excerpt":"Graph Neural Networks (GNNs) are widely used in graph representation learning. However, most GNN methods are designed for either homogeneous or heterogeneous graphs. In this paper, we propose a new model, Hop-Hop Relation-aware Graph Neural Network (HHR-GNN), to unify representation learning for these two types of graphs. HHR-GNN learns a personalized receptive field for each node by leveraging knowledge graph embedding to learn relation scores between the central node's representations at different hops. In neighborhood aggregation, our model simultaneously allows for hop-aware projection and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11147","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/2012.11147/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":"2012.11147","created_at":"2026-07-05T02:00:59.071417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11147v1","created_at":"2026-07-05T02:00:59.071417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11147","created_at":"2026-07-05T02:00:59.071417+00:00"},{"alias_kind":"pith_short_12","alias_value":"INCKBX2DT4LO","created_at":"2026-07-05T02:00:59.071417+00:00"},{"alias_kind":"pith_short_16","alias_value":"INCKBX2DT4LOGQS5","created_at":"2026-07-05T02:00:59.071417+00:00"},{"alias_kind":"pith_short_8","alias_value":"INCKBX2D","created_at":"2026-07-05T02:00:59.071417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06682","citing_title":"Learning Robust Heterogeneous Graph Representations via Contrastive-Reconstruction under Sparse Semantics","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INCKBX2DT4LOGQS5WJMJTD5XK5","json":"https://pith.science/pith/INCKBX2DT4LOGQS5WJMJTD5XK5.json","graph_json":"https://pith.science/api/pith-number/INCKBX2DT4LOGQS5WJMJTD5XK5/graph.json","events_json":"https://pith.science/api/pith-number/INCKBX2DT4LOGQS5WJMJTD5XK5/events.json","paper":"https://pith.science/paper/INCKBX2D"},"agent_actions":{"view_html":"https://pith.science/pith/INCKBX2DT4LOGQS5WJMJTD5XK5","download_json":"https://pith.science/pith/INCKBX2DT4LOGQS5WJMJTD5XK5.json","view_paper":"https://pith.science/paper/INCKBX2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11147&json=true","fetch_graph":"https://pith.science/api/pith-number/INCKBX2DT4LOGQS5WJMJTD5XK5/graph.json","fetch_events":"https://pith.science/api/pith-number/INCKBX2DT4LOGQS5WJMJTD5XK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INCKBX2DT4LOGQS5WJMJTD5XK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INCKBX2DT4LOGQS5WJMJTD5XK5/action/storage_attestation","attest_author":"https://pith.science/pith/INCKBX2DT4LOGQS5WJMJTD5XK5/action/author_attestation","sign_citation":"https://pith.science/pith/INCKBX2DT4LOGQS5WJMJTD5XK5/action/citation_signature","submit_replication":"https://pith.science/pith/INCKBX2DT4LOGQS5WJMJTD5XK5/action/replication_record"}},"created_at":"2026-07-05T02:00:59.071417+00:00","updated_at":"2026-07-05T02:00:59.071417+00:00"}