{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TIDOJOIMQ5YUJJWL7AK4P4FUHT","short_pith_number":"pith:TIDOJOIM","schema_version":"1.0","canonical_sha256":"9a06e4b90c877144a6cbf815c7f0b43ce150e841cade9596ee4746a55cb8d305","source":{"kind":"arxiv","id":"2006.07988","version":6},"attestation_state":"computed","paper":{"title":"Adaptive Universal Generalized PageRank Graph Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eli Chien, Jianhao Peng, Olgica Milenkovic, Pan Li","submitted_at":"2020-06-14T19:27:39Z","abstract_excerpt":"In many important graph data processing applications the acquired information includes both node features and observations of the graph topology. Graph neural networks (GNNs) are designed to exploit both sources of evidence but they do not optimally trade-off their utility and integrate them in a manner that is also universal. Here, universality refers to independence on homophily or heterophily graph assumptions. We address these issues by introducing a new Generalized PageRank (GPR) GNN architecture that adaptively learns the GPR weights so as to jointly optimize node feature and topological"},"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":"2006.07988","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T19:27:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0c414781d3f03dfc1f1cc735c068a74b9f7f467c43066c17c46a6f4b82b1af06","abstract_canon_sha256":"0ad37bcbc7acea48dbaec941b36816bd676275e747092a953f541bf2eed4dfc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:13.019621Z","signature_b64":"1nJmZhLvOwv0BJHIsdv/ts2JqVNBic0nivri6FNyn8l1wqMHrxyl/MUzIszHrgF/5/LIDB6sYvTr4AZlquYCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a06e4b90c877144a6cbf815c7f0b43ce150e841cade9596ee4746a55cb8d305","last_reissued_at":"2026-07-05T03:26:13.018556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:13.018556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Universal Generalized PageRank Graph Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eli Chien, Jianhao Peng, Olgica Milenkovic, Pan Li","submitted_at":"2020-06-14T19:27:39Z","abstract_excerpt":"In many important graph data processing applications the acquired information includes both node features and observations of the graph topology. Graph neural networks (GNNs) are designed to exploit both sources of evidence but they do not optimally trade-off their utility and integrate them in a manner that is also universal. Here, universality refers to independence on homophily or heterophily graph assumptions. We address these issues by introducing a new Generalized PageRank (GPR) GNN architecture that adaptively learns the GPR weights so as to jointly optimize node feature and topological"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07988","kind":"arxiv","version":6},"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/2006.07988/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":"2006.07988","created_at":"2026-07-05T03:26:13.018630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07988v6","created_at":"2026-07-05T03:26:13.018630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07988","created_at":"2026-07-05T03:26:13.018630+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIDOJOIMQ5YU","created_at":"2026-07-05T03:26:13.018630+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIDOJOIMQ5YUJJWL","created_at":"2026-07-05T03:26:13.018630+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIDOJOIM","created_at":"2026-07-05T03:26:13.018630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09051","citing_title":"Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00671","citing_title":"Multi-Label Node Classification with Label Influence Propagation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21247","citing_title":"Graph Navier Stokes Networks","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28134","citing_title":"Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12369","citing_title":"A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2501.15461","citing_title":"Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01123","citing_title":"Learning from Historical Activations in Graph Neural Networks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20248","citing_title":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21247","citing_title":"Graph Navier Stokes Networks","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16809","citing_title":"Informative Graph Structure Learning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2511.06443","citing_title":"How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19186","citing_title":"Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIDOJOIMQ5YUJJWL7AK4P4FUHT","json":"https://pith.science/pith/TIDOJOIMQ5YUJJWL7AK4P4FUHT.json","graph_json":"https://pith.science/api/pith-number/TIDOJOIMQ5YUJJWL7AK4P4FUHT/graph.json","events_json":"https://pith.science/api/pith-number/TIDOJOIMQ5YUJJWL7AK4P4FUHT/events.json","paper":"https://pith.science/paper/TIDOJOIM"},"agent_actions":{"view_html":"https://pith.science/pith/TIDOJOIMQ5YUJJWL7AK4P4FUHT","download_json":"https://pith.science/pith/TIDOJOIMQ5YUJJWL7AK4P4FUHT.json","view_paper":"https://pith.science/paper/TIDOJOIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07988&json=true","fetch_graph":"https://pith.science/api/pith-number/TIDOJOIMQ5YUJJWL7AK4P4FUHT/graph.json","fetch_events":"https://pith.science/api/pith-number/TIDOJOIMQ5YUJJWL7AK4P4FUHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIDOJOIMQ5YUJJWL7AK4P4FUHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIDOJOIMQ5YUJJWL7AK4P4FUHT/action/storage_attestation","attest_author":"https://pith.science/pith/TIDOJOIMQ5YUJJWL7AK4P4FUHT/action/author_attestation","sign_citation":"https://pith.science/pith/TIDOJOIMQ5YUJJWL7AK4P4FUHT/action/citation_signature","submit_replication":"https://pith.science/pith/TIDOJOIMQ5YUJJWL7AK4P4FUHT/action/replication_record"}},"created_at":"2026-07-05T03:26:13.018630+00:00","updated_at":"2026-07-05T03:26:13.018630+00:00"}