{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SJSGV45A5J2BR7DXJGPT5WM6PM","short_pith_number":"pith:SJSGV45A","schema_version":"1.0","canonical_sha256":"92646af3a0ea7418fc77499f3ed99e7b0e39aa191b2621a6018b9eb93d2b5389","source":{"kind":"arxiv","id":"2305.13656","version":1},"attestation_state":"computed","paper":{"title":"Link Prediction without Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Ambuj Singh, Arlei Silva, Mert Kosan, Zexi Huang","submitted_at":"2023-05-23T03:59:21Z","abstract_excerpt":"Link prediction, which consists of predicting edges based on graph features, is a fundamental task in many graph applications. As for several related problems, Graph Neural Networks (GNNs), which are based on an attribute-centric message-passing paradigm, have become the predominant framework for link prediction. GNNs have consistently outperformed traditional topology-based heuristics, but what contributes to their performance? Are there simpler approaches that achieve comparable or better results? To answer these questions, we first identify important limitations in how GNN-based link predic"},"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":"2305.13656","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T03:59:21Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"6e87b9321d0dc9952699606f7088e76ec597b643fedfde70a674ed63235c32ef","abstract_canon_sha256":"531a8cc162da63800da66205a0c7591358c4ee09a591f54aaea6f51a1a6b210f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:55.756443Z","signature_b64":"058E7Vc77ThsNw5GJ7fEURxQU8ao2omZHQYMMulVyLBaoxOPTNhxzVehDNhVfdd8B7IuoT/Y/Bg0+UhzBGb2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92646af3a0ea7418fc77499f3ed99e7b0e39aa191b2621a6018b9eb93d2b5389","last_reissued_at":"2026-07-05T06:12:55.755987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:55.755987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Link Prediction without Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Ambuj Singh, Arlei Silva, Mert Kosan, Zexi Huang","submitted_at":"2023-05-23T03:59:21Z","abstract_excerpt":"Link prediction, which consists of predicting edges based on graph features, is a fundamental task in many graph applications. As for several related problems, Graph Neural Networks (GNNs), which are based on an attribute-centric message-passing paradigm, have become the predominant framework for link prediction. GNNs have consistently outperformed traditional topology-based heuristics, but what contributes to their performance? Are there simpler approaches that achieve comparable or better results? To answer these questions, we first identify important limitations in how GNN-based link predic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13656","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/2305.13656/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":"2305.13656","created_at":"2026-07-05T06:12:55.756054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13656v1","created_at":"2026-07-05T06:12:55.756054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13656","created_at":"2026-07-05T06:12:55.756054+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJSGV45A5J2B","created_at":"2026-07-05T06:12:55.756054+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJSGV45A5J2BR7DX","created_at":"2026-07-05T06:12:55.756054+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJSGV45A","created_at":"2026-07-05T06:12:55.756054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06838","citing_title":"EPT Benchmark: Evaluation of Persian Trustworthiness in Large Language Models","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJSGV45A5J2BR7DXJGPT5WM6PM","json":"https://pith.science/pith/SJSGV45A5J2BR7DXJGPT5WM6PM.json","graph_json":"https://pith.science/api/pith-number/SJSGV45A5J2BR7DXJGPT5WM6PM/graph.json","events_json":"https://pith.science/api/pith-number/SJSGV45A5J2BR7DXJGPT5WM6PM/events.json","paper":"https://pith.science/paper/SJSGV45A"},"agent_actions":{"view_html":"https://pith.science/pith/SJSGV45A5J2BR7DXJGPT5WM6PM","download_json":"https://pith.science/pith/SJSGV45A5J2BR7DXJGPT5WM6PM.json","view_paper":"https://pith.science/paper/SJSGV45A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13656&json=true","fetch_graph":"https://pith.science/api/pith-number/SJSGV45A5J2BR7DXJGPT5WM6PM/graph.json","fetch_events":"https://pith.science/api/pith-number/SJSGV45A5J2BR7DXJGPT5WM6PM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJSGV45A5J2BR7DXJGPT5WM6PM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJSGV45A5J2BR7DXJGPT5WM6PM/action/storage_attestation","attest_author":"https://pith.science/pith/SJSGV45A5J2BR7DXJGPT5WM6PM/action/author_attestation","sign_citation":"https://pith.science/pith/SJSGV45A5J2BR7DXJGPT5WM6PM/action/citation_signature","submit_replication":"https://pith.science/pith/SJSGV45A5J2BR7DXJGPT5WM6PM/action/replication_record"}},"created_at":"2026-07-05T06:12:55.756054+00:00","updated_at":"2026-07-05T06:12:55.756054+00:00"}