{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XFR7ARZ6CINWXHDQYWJPBSKTOL","short_pith_number":"pith:XFR7ARZ6","schema_version":"1.0","canonical_sha256":"b963f0473e121b6b9c70c592f0c95372e56f171f31e87c3cbc4f69e3b91e33e2","source":{"kind":"arxiv","id":"2010.13993","version":2},"attestation_state":"computed","paper":{"title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Abhay Singh, Austin R. Benson, Horace He, Qian Huang, Ser-Nam Lim","submitted_at":"2020-10-27T02:10:52Z","abstract_excerpt":"Graph Neural Networks (GNNs) are the predominant technique for learning over graphs. However, there is relatively little understanding of why GNNs are successful in practice and whether they are necessary for good performance. Here, we show that for many standard transductive node classification benchmarks, we can exceed or match the performance of state-of-the-art GNNs by combining shallow models that ignore the graph structure with two simple post-processing steps that exploit correlation in the label structure: (i) an \"error correlation\" that spreads residual errors in training data to corr"},"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":"2010.13993","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T02:10:52Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"e5af807aadcba60dd140bf1c8c9d35034a61ffdc03407bdb3087ae0f41c22771","abstract_canon_sha256":"cdac06c4b0860bc291b58bec82bbf8a9a79a8d4edd02c4a283152036de08fa04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:30.347335Z","signature_b64":"bticYpVmaX9eBMRY4HC3f+rhDYfCQT2nI7moxG+55RcPCdJ4Pegn0Be0nNcTbQNsdFIUXSYVIu9J/jnPvZC4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b963f0473e121b6b9c70c592f0c95372e56f171f31e87c3cbc4f69e3b91e33e2","last_reissued_at":"2026-07-05T01:48:30.346918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:30.346918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Abhay Singh, Austin R. Benson, Horace He, Qian Huang, Ser-Nam Lim","submitted_at":"2020-10-27T02:10:52Z","abstract_excerpt":"Graph Neural Networks (GNNs) are the predominant technique for learning over graphs. However, there is relatively little understanding of why GNNs are successful in practice and whether they are necessary for good performance. Here, we show that for many standard transductive node classification benchmarks, we can exceed or match the performance of state-of-the-art GNNs by combining shallow models that ignore the graph structure with two simple post-processing steps that exploit correlation in the label structure: (i) an \"error correlation\" that spreads residual errors in training data to corr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13993","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/2010.13993/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":"2010.13993","created_at":"2026-07-05T01:48:30.346977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.13993v2","created_at":"2026-07-05T01:48:30.346977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13993","created_at":"2026-07-05T01:48:30.346977+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFR7ARZ6CINW","created_at":"2026-07-05T01:48:30.346977+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFR7ARZ6CINWXHDQ","created_at":"2026-07-05T01:48:30.346977+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFR7ARZ6","created_at":"2026-07-05T01:48:30.346977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05046","citing_title":"Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning","ref_index":162,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17071","citing_title":"AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01484","citing_title":"Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks","ref_index":157,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFR7ARZ6CINWXHDQYWJPBSKTOL","json":"https://pith.science/pith/XFR7ARZ6CINWXHDQYWJPBSKTOL.json","graph_json":"https://pith.science/api/pith-number/XFR7ARZ6CINWXHDQYWJPBSKTOL/graph.json","events_json":"https://pith.science/api/pith-number/XFR7ARZ6CINWXHDQYWJPBSKTOL/events.json","paper":"https://pith.science/paper/XFR7ARZ6"},"agent_actions":{"view_html":"https://pith.science/pith/XFR7ARZ6CINWXHDQYWJPBSKTOL","download_json":"https://pith.science/pith/XFR7ARZ6CINWXHDQYWJPBSKTOL.json","view_paper":"https://pith.science/paper/XFR7ARZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.13993&json=true","fetch_graph":"https://pith.science/api/pith-number/XFR7ARZ6CINWXHDQYWJPBSKTOL/graph.json","fetch_events":"https://pith.science/api/pith-number/XFR7ARZ6CINWXHDQYWJPBSKTOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFR7ARZ6CINWXHDQYWJPBSKTOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFR7ARZ6CINWXHDQYWJPBSKTOL/action/storage_attestation","attest_author":"https://pith.science/pith/XFR7ARZ6CINWXHDQYWJPBSKTOL/action/author_attestation","sign_citation":"https://pith.science/pith/XFR7ARZ6CINWXHDQYWJPBSKTOL/action/citation_signature","submit_replication":"https://pith.science/pith/XFR7ARZ6CINWXHDQYWJPBSKTOL/action/replication_record"}},"created_at":"2026-07-05T01:48:30.346977+00:00","updated_at":"2026-07-05T01:48:30.346977+00:00"}