{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EYLGG4ES53XRJCWS5ZBLHODOGY","short_pith_number":"pith:EYLGG4ES","schema_version":"1.0","canonical_sha256":"2616637092eeef148ad2ee42b3b86e362fe40860b41f3a9518cb19179660518c","source":{"kind":"arxiv","id":"2004.05718","version":5},"attestation_state":"computed","paper":{"title":"Principal Neighbourhood Aggregation for Graph Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dominique Beaini, Gabriele Corso, Luca Cavalleri, Petar Veli\\v{c}kovi\\'c, Pietro Li\\`o","submitted_at":"2020-04-12T23:30:00Z","abstract_excerpt":"Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on isomorphism tasks and countable feature spaces. We extend this theoretical framework to include continuous features - which occur regularly in real-world input domains and within the hidden layers of GNNs - and we demonstrate the requirement for multiple aggregation functions in this context. Accordingly, we propose Principal Neighbourhood Aggregation (PNA), a novel architecture combining multiple aggregators with degr"},"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":"2004.05718","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-12T23:30:00Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b273a0e05b6e55fefd2170b5dccce32cb0b4c49543d0b6cc7bc9ce8f6fac70e6","abstract_canon_sha256":"2a0db22eed0bb19d6438b7ee2f51938d05b9ea20cda7cc2873e4e6c35d284d1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:54.190715Z","signature_b64":"InkUOWHqF6mouON1BD+/xITikzIIMD503uxMmpv+BZdLGFunsEz79CtkMQos2d2DoDKQSh6vhGnpLS+S2FKoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2616637092eeef148ad2ee42b3b86e362fe40860b41f3a9518cb19179660518c","last_reissued_at":"2026-07-05T02:20:54.190101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:54.190101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Principal Neighbourhood Aggregation for Graph Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dominique Beaini, Gabriele Corso, Luca Cavalleri, Petar Veli\\v{c}kovi\\'c, Pietro Li\\`o","submitted_at":"2020-04-12T23:30:00Z","abstract_excerpt":"Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on isomorphism tasks and countable feature spaces. We extend this theoretical framework to include continuous features - which occur regularly in real-world input domains and within the hidden layers of GNNs - and we demonstrate the requirement for multiple aggregation functions in this context. Accordingly, we propose Principal Neighbourhood Aggregation (PNA), a novel architecture combining multiple aggregators with degr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05718","kind":"arxiv","version":5},"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/2004.05718/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":"2004.05718","created_at":"2026-07-05T02:20:54.190181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05718v5","created_at":"2026-07-05T02:20:54.190181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05718","created_at":"2026-07-05T02:20:54.190181+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYLGG4ES53XR","created_at":"2026-07-05T02:20:54.190181+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYLGG4ES53XRJCWS","created_at":"2026-07-05T02:20:54.190181+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYLGG4ES","created_at":"2026-07-05T02:20:54.190181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22429","citing_title":"Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01484","citing_title":"Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks","ref_index":221,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYLGG4ES53XRJCWS5ZBLHODOGY","json":"https://pith.science/pith/EYLGG4ES53XRJCWS5ZBLHODOGY.json","graph_json":"https://pith.science/api/pith-number/EYLGG4ES53XRJCWS5ZBLHODOGY/graph.json","events_json":"https://pith.science/api/pith-number/EYLGG4ES53XRJCWS5ZBLHODOGY/events.json","paper":"https://pith.science/paper/EYLGG4ES"},"agent_actions":{"view_html":"https://pith.science/pith/EYLGG4ES53XRJCWS5ZBLHODOGY","download_json":"https://pith.science/pith/EYLGG4ES53XRJCWS5ZBLHODOGY.json","view_paper":"https://pith.science/paper/EYLGG4ES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05718&json=true","fetch_graph":"https://pith.science/api/pith-number/EYLGG4ES53XRJCWS5ZBLHODOGY/graph.json","fetch_events":"https://pith.science/api/pith-number/EYLGG4ES53XRJCWS5ZBLHODOGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYLGG4ES53XRJCWS5ZBLHODOGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYLGG4ES53XRJCWS5ZBLHODOGY/action/storage_attestation","attest_author":"https://pith.science/pith/EYLGG4ES53XRJCWS5ZBLHODOGY/action/author_attestation","sign_citation":"https://pith.science/pith/EYLGG4ES53XRJCWS5ZBLHODOGY/action/citation_signature","submit_replication":"https://pith.science/pith/EYLGG4ES53XRJCWS5ZBLHODOGY/action/replication_record"}},"created_at":"2026-07-05T02:20:54.190181+00:00","updated_at":"2026-07-05T02:20:54.190181+00:00"}