{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XMX3C64MG7WVDIGDZ7SXIVLH4T","short_pith_number":"pith:XMX3C64M","schema_version":"1.0","canonical_sha256":"bb2fb17b8c37ed51a0c3cfe5745567e4ead9aa1a9cf81e56a9b455f0f95d0f8b","source":{"kind":"arxiv","id":"1811.01287","version":1},"attestation_state":"computed","paper":{"title":"Towards Sparse Hierarchical Graph Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SI"],"primary_cat":"stat.ML","authors_text":"C\\u{a}t\\u{a}lina Cangea, Nikola Jovanovi\\'c, Petar Veli\\v{c}kovi\\'c, Pietro Li\\`o, Thomas Kipf","submitted_at":"2018-11-03T21:39:43Z","abstract_excerpt":"Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks. While novel approaches to learning node embeddings are highly suitable for node classification and link prediction, their application to graph classification (predicting a single label for the entire graph) remains mostly rudimentary, typically using a single global pooling step to aggregate node features or a hand-designed, fixed heuristic for hierarchical coarsening of the graph structure. An important step towards a"},"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":"1811.01287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-03T21:39:43Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SI"],"title_canon_sha256":"21f1f7485b7655caacee2d6493257b241715613a838a21875ab8fe35bb724f24","abstract_canon_sha256":"c23bdfc0133f569ba17e30960d08c2567390ef268c7a510980b8c704c39a497c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:34.754626Z","signature_b64":"FDe5MWQiDrt13whZD5mXJAp9kO+SqpagDAorFmLasXRnqxx9xhxsil/y4MNmdvyNYNxrdZaGOmSOdw01cWuhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb2fb17b8c37ed51a0c3cfe5745567e4ead9aa1a9cf81e56a9b455f0f95d0f8b","last_reissued_at":"2026-05-18T00:01:34.754050Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:34.754050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Sparse Hierarchical Graph Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SI"],"primary_cat":"stat.ML","authors_text":"C\\u{a}t\\u{a}lina Cangea, Nikola Jovanovi\\'c, Petar Veli\\v{c}kovi\\'c, Pietro Li\\`o, Thomas Kipf","submitted_at":"2018-11-03T21:39:43Z","abstract_excerpt":"Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks. While novel approaches to learning node embeddings are highly suitable for node classification and link prediction, their application to graph classification (predicting a single label for the entire graph) remains mostly rudimentary, typically using a single global pooling step to aggregate node features or a hand-designed, fixed heuristic for hierarchical coarsening of the graph structure. An important step towards a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01287","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":""},"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":"1811.01287","created_at":"2026-05-18T00:01:34.754150+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01287v1","created_at":"2026-05-18T00:01:34.754150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01287","created_at":"2026-05-18T00:01:34.754150+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMX3C64MG7WV","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMX3C64MG7WVDIGD","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMX3C64M","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.01661","citing_title":"Graph Neural Network for Interpreting Task-fMRI Biomarkers","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2210.15304","citing_title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2501.00773","citing_title":"OpenGLT: A Comprehensive Benchmark of Graph Neural Networks for Graph-Level Tasks","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10091","citing_title":"TopoU-Net: a U-Net architecture for topological domains","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMX3C64MG7WVDIGDZ7SXIVLH4T","json":"https://pith.science/pith/XMX3C64MG7WVDIGDZ7SXIVLH4T.json","graph_json":"https://pith.science/api/pith-number/XMX3C64MG7WVDIGDZ7SXIVLH4T/graph.json","events_json":"https://pith.science/api/pith-number/XMX3C64MG7WVDIGDZ7SXIVLH4T/events.json","paper":"https://pith.science/paper/XMX3C64M"},"agent_actions":{"view_html":"https://pith.science/pith/XMX3C64MG7WVDIGDZ7SXIVLH4T","download_json":"https://pith.science/pith/XMX3C64MG7WVDIGDZ7SXIVLH4T.json","view_paper":"https://pith.science/paper/XMX3C64M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01287&json=true","fetch_graph":"https://pith.science/api/pith-number/XMX3C64MG7WVDIGDZ7SXIVLH4T/graph.json","fetch_events":"https://pith.science/api/pith-number/XMX3C64MG7WVDIGDZ7SXIVLH4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMX3C64MG7WVDIGDZ7SXIVLH4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMX3C64MG7WVDIGDZ7SXIVLH4T/action/storage_attestation","attest_author":"https://pith.science/pith/XMX3C64MG7WVDIGDZ7SXIVLH4T/action/author_attestation","sign_citation":"https://pith.science/pith/XMX3C64MG7WVDIGDZ7SXIVLH4T/action/citation_signature","submit_replication":"https://pith.science/pith/XMX3C64MG7WVDIGDZ7SXIVLH4T/action/replication_record"}},"created_at":"2026-05-18T00:01:34.754150+00:00","updated_at":"2026-05-18T00:01:34.754150+00:00"}