{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HJLKYV26ILY5QJTHUCMHLIL3D6","short_pith_number":"pith:HJLKYV26","schema_version":"1.0","canonical_sha256":"3a56ac575e42f1d82667a09875a17b1f94b012fd7b4875b9593dd301464bb5b3","source":{"kind":"arxiv","id":"2110.04375","version":2},"attestation_state":"computed","paper":{"title":"Neural Link Prediction with Walk Pooling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Cheng Shi, Ivan Dokmani\\'c, Liming Pan","submitted_at":"2021-10-08T20:52:12Z","abstract_excerpt":"Graph neural networks achieve high accuracy in link prediction by jointly leveraging graph topology and node attributes. Topology, however, is represented indirectly; state-of-the-art methods based on subgraph classification label nodes with distance to the target link, so that, although topological information is present, it is tempered by pooling. This makes it challenging to leverage features like loops and motifs associated with network formation mechanisms. We propose a link prediction algorithm based on a new pooling scheme called WalkPool. WalkPool combines the expressivity of topologic"},"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":"2110.04375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T20:52:12Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"d203affe7d2e24453d73a5cd8e7e6b17d7d41345f392b41efb8c64fbb7436313","abstract_canon_sha256":"c823f9633eca88be1b0300a56d378f3df1239dcfbbe71e27848927ed0692df1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:35.536429Z","signature_b64":"kh1jPHrP3+A1Vw9BVNtsNclYz/z77SBz2pikYWEc4bEQb7pRRCtpFd1QD1YI7o6ntK4VKlpgNzN/65E3ppWoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a56ac575e42f1d82667a09875a17b1f94b012fd7b4875b9593dd301464bb5b3","last_reissued_at":"2026-07-05T04:05:35.535990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:35.535990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Link Prediction with Walk Pooling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Cheng Shi, Ivan Dokmani\\'c, Liming Pan","submitted_at":"2021-10-08T20:52:12Z","abstract_excerpt":"Graph neural networks achieve high accuracy in link prediction by jointly leveraging graph topology and node attributes. Topology, however, is represented indirectly; state-of-the-art methods based on subgraph classification label nodes with distance to the target link, so that, although topological information is present, it is tempered by pooling. This makes it challenging to leverage features like loops and motifs associated with network formation mechanisms. We propose a link prediction algorithm based on a new pooling scheme called WalkPool. WalkPool combines the expressivity of topologic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04375","kind":"arxiv","version":2},"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/2110.04375/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":"2110.04375","created_at":"2026-07-05T04:05:35.536048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.04375v2","created_at":"2026-07-05T04:05:35.536048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04375","created_at":"2026-07-05T04:05:35.536048+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJLKYV26ILY5","created_at":"2026-07-05T04:05:35.536048+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJLKYV26ILY5QJTH","created_at":"2026-07-05T04:05:35.536048+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJLKYV26","created_at":"2026-07-05T04:05:35.536048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09457","citing_title":"RAwR: Role-Aware Rewiring via Approximate Equitable Partition","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09408","citing_title":"GravityGraphSAGE: Link Prediction in Directed Attributed Graphs","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJLKYV26ILY5QJTHUCMHLIL3D6","json":"https://pith.science/pith/HJLKYV26ILY5QJTHUCMHLIL3D6.json","graph_json":"https://pith.science/api/pith-number/HJLKYV26ILY5QJTHUCMHLIL3D6/graph.json","events_json":"https://pith.science/api/pith-number/HJLKYV26ILY5QJTHUCMHLIL3D6/events.json","paper":"https://pith.science/paper/HJLKYV26"},"agent_actions":{"view_html":"https://pith.science/pith/HJLKYV26ILY5QJTHUCMHLIL3D6","download_json":"https://pith.science/pith/HJLKYV26ILY5QJTHUCMHLIL3D6.json","view_paper":"https://pith.science/paper/HJLKYV26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.04375&json=true","fetch_graph":"https://pith.science/api/pith-number/HJLKYV26ILY5QJTHUCMHLIL3D6/graph.json","fetch_events":"https://pith.science/api/pith-number/HJLKYV26ILY5QJTHUCMHLIL3D6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJLKYV26ILY5QJTHUCMHLIL3D6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJLKYV26ILY5QJTHUCMHLIL3D6/action/storage_attestation","attest_author":"https://pith.science/pith/HJLKYV26ILY5QJTHUCMHLIL3D6/action/author_attestation","sign_citation":"https://pith.science/pith/HJLKYV26ILY5QJTHUCMHLIL3D6/action/citation_signature","submit_replication":"https://pith.science/pith/HJLKYV26ILY5QJTHUCMHLIL3D6/action/replication_record"}},"created_at":"2026-07-05T04:05:35.536048+00:00","updated_at":"2026-07-05T04:05:35.536048+00:00"}