{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:R5ZJVTIKMZPZBAGC4UJGNY4AWF","short_pith_number":"pith:R5ZJVTIK","schema_version":"1.0","canonical_sha256":"8f729acd0a665f9080c2e51266e380b168533bcb2d68ec0fa47c063f5c9fd867","source":{"kind":"arxiv","id":"2102.11533","version":4},"attestation_state":"computed","paper":{"title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinheon Baek, Minki Kang, Sung Ju Hwang","submitted_at":"2021-02-23T07:45:58Z","abstract_excerpt":"Graph neural networks have been widely used on modeling graph data, achieving impressive results on node classification and link prediction tasks. Yet, obtaining an accurate representation for a graph further requires a pooling function that maps a set of node representations into a compact form. A simple sum or average over all node representations considers all node features equally without consideration of their task relevance, and any structural dependencies among them. Recently proposed hierarchical graph pooling methods, on the other hand, may yield the same representation for two differ"},"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":"2102.11533","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-23T07:45:58Z","cross_cats_sorted":[],"title_canon_sha256":"0448cdc5d81bb3a5a41cbe77ec4614464cc0e8f8e511a40f4312664442fe74d7","abstract_canon_sha256":"4e13f7a6cdc06b63adee581ef2b1c07c3cf7e5c74a4358c89483118eff26e8c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:42.159463Z","signature_b64":"Tv8WHQBjrjlBDPCdRSeq2FfwTmXQPth3vWF+8wtqSvGNszkVvFijPf2KEq08N8d/m4IJ9jvKb3YVN2C6GvsCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f729acd0a665f9080c2e51266e380b168533bcb2d68ec0fa47c063f5c9fd867","last_reissued_at":"2026-07-05T02:52:42.158953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:42.158953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinheon Baek, Minki Kang, Sung Ju Hwang","submitted_at":"2021-02-23T07:45:58Z","abstract_excerpt":"Graph neural networks have been widely used on modeling graph data, achieving impressive results on node classification and link prediction tasks. Yet, obtaining an accurate representation for a graph further requires a pooling function that maps a set of node representations into a compact form. A simple sum or average over all node representations considers all node features equally without consideration of their task relevance, and any structural dependencies among them. Recently proposed hierarchical graph pooling methods, on the other hand, may yield the same representation for two differ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11533","kind":"arxiv","version":4},"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/2102.11533/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":"2102.11533","created_at":"2026-07-05T02:52:42.159011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.11533v4","created_at":"2026-07-05T02:52:42.159011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11533","created_at":"2026-07-05T02:52:42.159011+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5ZJVTIKMZPZ","created_at":"2026-07-05T02:52:42.159011+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5ZJVTIKMZPZBAGC","created_at":"2026-07-05T02:52:42.159011+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5ZJVTIK","created_at":"2026-07-05T02:52:42.159011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00808","citing_title":"Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00656","citing_title":"DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01484","citing_title":"Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5ZJVTIKMZPZBAGC4UJGNY4AWF","json":"https://pith.science/pith/R5ZJVTIKMZPZBAGC4UJGNY4AWF.json","graph_json":"https://pith.science/api/pith-number/R5ZJVTIKMZPZBAGC4UJGNY4AWF/graph.json","events_json":"https://pith.science/api/pith-number/R5ZJVTIKMZPZBAGC4UJGNY4AWF/events.json","paper":"https://pith.science/paper/R5ZJVTIK"},"agent_actions":{"view_html":"https://pith.science/pith/R5ZJVTIKMZPZBAGC4UJGNY4AWF","download_json":"https://pith.science/pith/R5ZJVTIKMZPZBAGC4UJGNY4AWF.json","view_paper":"https://pith.science/paper/R5ZJVTIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.11533&json=true","fetch_graph":"https://pith.science/api/pith-number/R5ZJVTIKMZPZBAGC4UJGNY4AWF/graph.json","fetch_events":"https://pith.science/api/pith-number/R5ZJVTIKMZPZBAGC4UJGNY4AWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5ZJVTIKMZPZBAGC4UJGNY4AWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5ZJVTIKMZPZBAGC4UJGNY4AWF/action/storage_attestation","attest_author":"https://pith.science/pith/R5ZJVTIKMZPZBAGC4UJGNY4AWF/action/author_attestation","sign_citation":"https://pith.science/pith/R5ZJVTIKMZPZBAGC4UJGNY4AWF/action/citation_signature","submit_replication":"https://pith.science/pith/R5ZJVTIKMZPZBAGC4UJGNY4AWF/action/replication_record"}},"created_at":"2026-07-05T02:52:42.159011+00:00","updated_at":"2026-07-05T02:52:42.159011+00:00"}