{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EYNSXLXNTUUDAW6NMN5GVM65TN","short_pith_number":"pith:EYNSXLXN","schema_version":"1.0","canonical_sha256":"261b2baeed9d28305bcd637a6ab3dd9b65c575a3c2e3f647c6ac8b24d417166e","source":{"kind":"arxiv","id":"2010.11418","version":1},"attestation_state":"computed","paper":{"title":"Rethinking pooling in graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Amauri H. Souza, Diego Mesquita, Samuel Kaski","submitted_at":"2020-10-22T03:48:56Z","abstract_excerpt":"Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a cluster assignment problem, extending the idea of local patches in regular grids to graphs. Despite the wide adherence to this design choice, no work has rigorously evaluated its influence on the success of GNNs. In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Stri"},"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":"2010.11418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T03:48:56Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5b15b525f3c83daef2e729c0773ffa9aeff56bbeeca062d550e70e4e7ff942c7","abstract_canon_sha256":"46860a7b28daeaf45ab0dc51e5930e6912069c86652b3a6c40850515aa1d0329"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:09.926238Z","signature_b64":"2YY5nhNPfOeX4lpD6UiF68oE6DUQR2aTMFlOzGhE7S5EfDejt1hv5NrhnBvuBT565XV4k90hBB8USmlCrpzTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"261b2baeed9d28305bcd637a6ab3dd9b65c575a3c2e3f647c6ac8b24d417166e","last_reissued_at":"2026-07-05T01:45:09.925807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:09.925807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking pooling in graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Amauri H. Souza, Diego Mesquita, Samuel Kaski","submitted_at":"2020-10-22T03:48:56Z","abstract_excerpt":"Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a cluster assignment problem, extending the idea of local patches in regular grids to graphs. Despite the wide adherence to this design choice, no work has rigorously evaluated its influence on the success of GNNs. In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Stri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11418","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/2010.11418/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":"2010.11418","created_at":"2026-07-05T01:45:09.925861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.11418v1","created_at":"2026-07-05T01:45:09.925861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11418","created_at":"2026-07-05T01:45:09.925861+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYNSXLXNTUUD","created_at":"2026-07-05T01:45:09.925861+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYNSXLXNTUUDAW6N","created_at":"2026-07-05T01:45:09.925861+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYNSXLXN","created_at":"2026-07-05T01:45:09.925861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22429","citing_title":"Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation","ref_index":262,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYNSXLXNTUUDAW6NMN5GVM65TN","json":"https://pith.science/pith/EYNSXLXNTUUDAW6NMN5GVM65TN.json","graph_json":"https://pith.science/api/pith-number/EYNSXLXNTUUDAW6NMN5GVM65TN/graph.json","events_json":"https://pith.science/api/pith-number/EYNSXLXNTUUDAW6NMN5GVM65TN/events.json","paper":"https://pith.science/paper/EYNSXLXN"},"agent_actions":{"view_html":"https://pith.science/pith/EYNSXLXNTUUDAW6NMN5GVM65TN","download_json":"https://pith.science/pith/EYNSXLXNTUUDAW6NMN5GVM65TN.json","view_paper":"https://pith.science/paper/EYNSXLXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.11418&json=true","fetch_graph":"https://pith.science/api/pith-number/EYNSXLXNTUUDAW6NMN5GVM65TN/graph.json","fetch_events":"https://pith.science/api/pith-number/EYNSXLXNTUUDAW6NMN5GVM65TN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYNSXLXNTUUDAW6NMN5GVM65TN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYNSXLXNTUUDAW6NMN5GVM65TN/action/storage_attestation","attest_author":"https://pith.science/pith/EYNSXLXNTUUDAW6NMN5GVM65TN/action/author_attestation","sign_citation":"https://pith.science/pith/EYNSXLXNTUUDAW6NMN5GVM65TN/action/citation_signature","submit_replication":"https://pith.science/pith/EYNSXLXNTUUDAW6NMN5GVM65TN/action/replication_record"}},"created_at":"2026-07-05T01:45:09.925861+00:00","updated_at":"2026-07-05T01:45:09.925861+00:00"}