{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KPXDCDPXSQGNU6UJAXJ6ZBXDUD","short_pith_number":"pith:KPXDCDPX","schema_version":"1.0","canonical_sha256":"53ee310df7940cda7a8905d3ec86e3a0cc74b76218219abc67bcd241044cdacd","source":{"kind":"arxiv","id":"1911.05256","version":1},"attestation_state":"computed","paper":{"title":"A Hierarchy of Graph Neural Networks Based on Learnable Local Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander M. Rush, Jiawei Zhou, Meng Dong, Michael Lingzhi Li","submitted_at":"2019-11-13T02:22:54Z","abstract_excerpt":"Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to compare different architectures and how to construct GNNs systematically. Here, we propose a hierarchy of GNNs based on their aggregation regions. We derive theoretical results about the discriminative power and feature representation capabilities of each class. Then, we show how this framework can be utilized to systematically construct arbitrarily powerful GNN"},"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":"1911.05256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-13T02:22:54Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"ca65b4cac97c3e7ec2d82a3256a50141e08b6d371e3e93fcc3d915f2069f3d4d","abstract_canon_sha256":"d37390fcd800b199a2e8a1ace1a9b6eff8cc7370bcb7893234f02134a09c2a12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:55.484963Z","signature_b64":"nYp24nw3Q2yEQ1eVTvPyD862krrhv4gtORD2WtUIXJxCjJgupkcwk43IvkuJQsTGIqeDzo0v27XD/mxvqzL8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53ee310df7940cda7a8905d3ec86e3a0cc74b76218219abc67bcd241044cdacd","last_reissued_at":"2026-07-05T00:18:55.484521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:55.484521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hierarchy of Graph Neural Networks Based on Learnable Local Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander M. Rush, Jiawei Zhou, Meng Dong, Michael Lingzhi Li","submitted_at":"2019-11-13T02:22:54Z","abstract_excerpt":"Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to compare different architectures and how to construct GNNs systematically. Here, we propose a hierarchy of GNNs based on their aggregation regions. We derive theoretical results about the discriminative power and feature representation capabilities of each class. Then, we show how this framework can be utilized to systematically construct arbitrarily powerful GNN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05256","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/1911.05256/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":"1911.05256","created_at":"2026-07-05T00:18:55.484577+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05256v1","created_at":"2026-07-05T00:18:55.484577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05256","created_at":"2026-07-05T00:18:55.484577+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPXDCDPXSQGN","created_at":"2026-07-05T00:18:55.484577+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPXDCDPXSQGNU6UJ","created_at":"2026-07-05T00:18:55.484577+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPXDCDPX","created_at":"2026-07-05T00:18:55.484577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20635","citing_title":"NetFlowGen: Leveraging Generative Pre-training for Network Traffic Dynamics","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPXDCDPXSQGNU6UJAXJ6ZBXDUD","json":"https://pith.science/pith/KPXDCDPXSQGNU6UJAXJ6ZBXDUD.json","graph_json":"https://pith.science/api/pith-number/KPXDCDPXSQGNU6UJAXJ6ZBXDUD/graph.json","events_json":"https://pith.science/api/pith-number/KPXDCDPXSQGNU6UJAXJ6ZBXDUD/events.json","paper":"https://pith.science/paper/KPXDCDPX"},"agent_actions":{"view_html":"https://pith.science/pith/KPXDCDPXSQGNU6UJAXJ6ZBXDUD","download_json":"https://pith.science/pith/KPXDCDPXSQGNU6UJAXJ6ZBXDUD.json","view_paper":"https://pith.science/paper/KPXDCDPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05256&json=true","fetch_graph":"https://pith.science/api/pith-number/KPXDCDPXSQGNU6UJAXJ6ZBXDUD/graph.json","fetch_events":"https://pith.science/api/pith-number/KPXDCDPXSQGNU6UJAXJ6ZBXDUD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPXDCDPXSQGNU6UJAXJ6ZBXDUD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPXDCDPXSQGNU6UJAXJ6ZBXDUD/action/storage_attestation","attest_author":"https://pith.science/pith/KPXDCDPXSQGNU6UJAXJ6ZBXDUD/action/author_attestation","sign_citation":"https://pith.science/pith/KPXDCDPXSQGNU6UJAXJ6ZBXDUD/action/citation_signature","submit_replication":"https://pith.science/pith/KPXDCDPXSQGNU6UJAXJ6ZBXDUD/action/replication_record"}},"created_at":"2026-07-05T00:18:55.484577+00:00","updated_at":"2026-07-05T00:18:55.484577+00:00"}