{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PYUUBF7DCDIFHEN54AHSFYR4GD","short_pith_number":"pith:PYUUBF7D","schema_version":"1.0","canonical_sha256":"7e294097e310d05391bde00f22e23c30cac296c723d166e32ead9cdef3b1826a","source":{"kind":"arxiv","id":"2007.01570","version":2},"attestation_state":"computed","paper":{"title":"Scaling Graph Neural Networks with Approximate PageRank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksandar Bojchevski, Amol Kapoor, Benedek R\\'ozemberczki, Bryan Perozzi, Johannes Gasteiger, Martin Blais, Michal Lukasik, Stephan G\\\"unnemann","submitted_at":"2020-07-03T09:30:07Z","abstract_excerpt":"Graph neural networks (GNNs) have emerged as a powerful approach for solving many network mining tasks. However, learning on large graphs remains a challenge - many recently proposed scalable GNN approaches rely on an expensive message-passing procedure to propagate information through the graph. We present the PPRGo model which utilizes an efficient approximation of information diffusion in GNNs resulting in significant speed gains while maintaining state-of-the-art prediction performance. In addition to being faster, PPRGo is inherently scalable, and can be trivially parallelized for large d"},"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":"2007.01570","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T09:30:07Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"db3d4b1ac1cf97b6812bd31bc42ce8f6e8eb52f1ecc2f33fd9bfc8e30fd74998","abstract_canon_sha256":"f6d27e6adac35aff51d82e1f04b3642568f590582105813bb013a5b136eddc1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:23.277941Z","signature_b64":"1VAE+1VCVi+UaerFF5O/h3nyfu0lo7Pi+STeX701L6WnEnBipZ9/toMbFL8NR+w4wrOEdfhJ/tOZu5LaXAFwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e294097e310d05391bde00f22e23c30cac296c723d166e32ead9cdef3b1826a","last_reissued_at":"2026-07-05T04:11:23.277440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:23.277440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Graph Neural Networks with Approximate PageRank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksandar Bojchevski, Amol Kapoor, Benedek R\\'ozemberczki, Bryan Perozzi, Johannes Gasteiger, Martin Blais, Michal Lukasik, Stephan G\\\"unnemann","submitted_at":"2020-07-03T09:30:07Z","abstract_excerpt":"Graph neural networks (GNNs) have emerged as a powerful approach for solving many network mining tasks. However, learning on large graphs remains a challenge - many recently proposed scalable GNN approaches rely on an expensive message-passing procedure to propagate information through the graph. We present the PPRGo model which utilizes an efficient approximation of information diffusion in GNNs resulting in significant speed gains while maintaining state-of-the-art prediction performance. In addition to being faster, PPRGo is inherently scalable, and can be trivially parallelized for large d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01570","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/2007.01570/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":"2007.01570","created_at":"2026-07-05T04:11:23.277497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.01570v2","created_at":"2026-07-05T04:11:23.277497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01570","created_at":"2026-07-05T04:11:23.277497+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYUUBF7DCDIF","created_at":"2026-07-05T04:11:23.277497+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYUUBF7DCDIFHEN5","created_at":"2026-07-05T04:11:23.277497+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYUUBF7D","created_at":"2026-07-05T04:11:23.277497+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/PYUUBF7DCDIFHEN54AHSFYR4GD","json":"https://pith.science/pith/PYUUBF7DCDIFHEN54AHSFYR4GD.json","graph_json":"https://pith.science/api/pith-number/PYUUBF7DCDIFHEN54AHSFYR4GD/graph.json","events_json":"https://pith.science/api/pith-number/PYUUBF7DCDIFHEN54AHSFYR4GD/events.json","paper":"https://pith.science/paper/PYUUBF7D"},"agent_actions":{"view_html":"https://pith.science/pith/PYUUBF7DCDIFHEN54AHSFYR4GD","download_json":"https://pith.science/pith/PYUUBF7DCDIFHEN54AHSFYR4GD.json","view_paper":"https://pith.science/paper/PYUUBF7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.01570&json=true","fetch_graph":"https://pith.science/api/pith-number/PYUUBF7DCDIFHEN54AHSFYR4GD/graph.json","fetch_events":"https://pith.science/api/pith-number/PYUUBF7DCDIFHEN54AHSFYR4GD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYUUBF7DCDIFHEN54AHSFYR4GD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYUUBF7DCDIFHEN54AHSFYR4GD/action/storage_attestation","attest_author":"https://pith.science/pith/PYUUBF7DCDIFHEN54AHSFYR4GD/action/author_attestation","sign_citation":"https://pith.science/pith/PYUUBF7DCDIFHEN54AHSFYR4GD/action/citation_signature","submit_replication":"https://pith.science/pith/PYUUBF7DCDIFHEN54AHSFYR4GD/action/replication_record"}},"created_at":"2026-07-05T04:11:23.277497+00:00","updated_at":"2026-07-05T04:11:23.277497+00:00"}