{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TPHYTWX57OHIJCRGZKZP34NK4F","short_pith_number":"pith:TPHYTWX5","schema_version":"1.0","canonical_sha256":"9bcf89dafdfb8e848a26cab2fdf1aae155dc676a05bd3868efdd593e425a2b50","source":{"kind":"arxiv","id":"2402.08583","version":2},"attestation_state":"computed","paper":{"title":"Mixture of Link Predictors on Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoyu Han, Harry Shomer, Hui Liu, Jiliang Tang, Juanhui Li, Li Ma, Xiaofeng Gao","submitted_at":"2024-02-13T16:36:50Z","abstract_excerpt":"Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning. Heuristic methods, leveraging a range of different pairwise measures such as common neighbors and shortest paths, often rival the performance of vanilla Graph Neural Networks (GNNs). Therefore, recent advancements in GNNs for link prediction (GNN4LP) have primarily focused on integrating one or a few types of pairwise information. In this work, we reveal that different node pairs within the same dataset necessitate varied pairwise information for accurate prediction and models"},"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":"2402.08583","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T16:36:50Z","cross_cats_sorted":[],"title_canon_sha256":"d673863a8aed57eef6b0bfcb65901a95e809418db61398821b00c560b9d9fba7","abstract_canon_sha256":"f1ca098be250c268966c71daf6c8b67fb76d073746419b67064cf91bf9f86021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:54.596604Z","signature_b64":"/cwhsd/Ea0oCF5ELQte+u2lYHjVKGfyUtS8co0O7HTDl8BDN87tBuLecbeCrRNm4xeT7NpNQLMGm2VK64RuQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bcf89dafdfb8e848a26cab2fdf1aae155dc676a05bd3868efdd593e425a2b50","last_reissued_at":"2026-07-05T09:55:54.596034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:54.596034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture of Link Predictors on Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoyu Han, Harry Shomer, Hui Liu, Jiliang Tang, Juanhui Li, Li Ma, Xiaofeng Gao","submitted_at":"2024-02-13T16:36:50Z","abstract_excerpt":"Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning. Heuristic methods, leveraging a range of different pairwise measures such as common neighbors and shortest paths, often rival the performance of vanilla Graph Neural Networks (GNNs). Therefore, recent advancements in GNNs for link prediction (GNN4LP) have primarily focused on integrating one or a few types of pairwise information. In this work, we reveal that different node pairs within the same dataset necessitate varied pairwise information for accurate prediction and models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08583","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/2402.08583/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":"2402.08583","created_at":"2026-07-05T09:55:54.596088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08583v2","created_at":"2026-07-05T09:55:54.596088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08583","created_at":"2026-07-05T09:55:54.596088+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPHYTWX57OHI","created_at":"2026-07-05T09:55:54.596088+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPHYTWX57OHIJCRG","created_at":"2026-07-05T09:55:54.596088+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPHYTWX5","created_at":"2026-07-05T09:55:54.596088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08298","citing_title":"H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPHYTWX57OHIJCRGZKZP34NK4F","json":"https://pith.science/pith/TPHYTWX57OHIJCRGZKZP34NK4F.json","graph_json":"https://pith.science/api/pith-number/TPHYTWX57OHIJCRGZKZP34NK4F/graph.json","events_json":"https://pith.science/api/pith-number/TPHYTWX57OHIJCRGZKZP34NK4F/events.json","paper":"https://pith.science/paper/TPHYTWX5"},"agent_actions":{"view_html":"https://pith.science/pith/TPHYTWX57OHIJCRGZKZP34NK4F","download_json":"https://pith.science/pith/TPHYTWX57OHIJCRGZKZP34NK4F.json","view_paper":"https://pith.science/paper/TPHYTWX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08583&json=true","fetch_graph":"https://pith.science/api/pith-number/TPHYTWX57OHIJCRGZKZP34NK4F/graph.json","fetch_events":"https://pith.science/api/pith-number/TPHYTWX57OHIJCRGZKZP34NK4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPHYTWX57OHIJCRGZKZP34NK4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPHYTWX57OHIJCRGZKZP34NK4F/action/storage_attestation","attest_author":"https://pith.science/pith/TPHYTWX57OHIJCRGZKZP34NK4F/action/author_attestation","sign_citation":"https://pith.science/pith/TPHYTWX57OHIJCRGZKZP34NK4F/action/citation_signature","submit_replication":"https://pith.science/pith/TPHYTWX57OHIJCRGZKZP34NK4F/action/replication_record"}},"created_at":"2026-07-05T09:55:54.596088+00:00","updated_at":"2026-07-05T09:55:54.596088+00:00"}