{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:M2UYY7YCS2VT6IEIZUW3NODERX","short_pith_number":"pith:M2UYY7YC","schema_version":"1.0","canonical_sha256":"66a98c7f0296ab3f2088cd2db6b8648df812e80169efae3b3c121feb4f53d047","source":{"kind":"arxiv","id":"1909.12223","version":2},"attestation_state":"computed","paper":{"title":"PairNorm: Tackling Oversmoothing in GNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Leman Akoglu, Lingxiao Zhao","submitted_at":"2019-09-26T16:20:37Z","abstract_excerpt":"The performance of graph neural nets (GNNs) is known to gradually decrease with increasing number of layers. This decay is partly attributed to oversmoothing, where repeated graph convolutions eventually make node embeddings indistinguishable. We take a closer look at two different interpretations, aiming to quantify oversmoothing. Our main contribution is PairNorm, a novel normalization layer that is based on a careful analysis of the graph convolution operator, which prevents all node embeddings from becoming too similar. What is more, PairNorm is fast, easy to implement without any change t"},"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":"1909.12223","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T16:20:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e6583bfcb8b7727320c0077680b39c9ef920782374bdb6f73211f8e9c53065b9","abstract_canon_sha256":"efc251ccd1397aa03d6f3c403799dca7dda6e2d871af007d53cfc701099a26ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:25.641644Z","signature_b64":"qRSX0/m75tXXbpJqQZZ2yhI4Pxp9kPPEGPGIwT8fQe+s20TBWBRbMqwewT6A8kGCfwcLCAAR8iInwSPtU2UWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66a98c7f0296ab3f2088cd2db6b8648df812e80169efae3b3c121feb4f53d047","last_reissued_at":"2026-07-05T00:40:25.641175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:25.641175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PairNorm: Tackling Oversmoothing in GNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Leman Akoglu, Lingxiao Zhao","submitted_at":"2019-09-26T16:20:37Z","abstract_excerpt":"The performance of graph neural nets (GNNs) is known to gradually decrease with increasing number of layers. This decay is partly attributed to oversmoothing, where repeated graph convolutions eventually make node embeddings indistinguishable. We take a closer look at two different interpretations, aiming to quantify oversmoothing. Our main contribution is PairNorm, a novel normalization layer that is based on a careful analysis of the graph convolution operator, which prevents all node embeddings from becoming too similar. What is more, PairNorm is fast, easy to implement without any change t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12223","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/1909.12223/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":"1909.12223","created_at":"2026-07-05T00:40:25.641247+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12223v2","created_at":"2026-07-05T00:40:25.641247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12223","created_at":"2026-07-05T00:40:25.641247+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2UYY7YCS2VT","created_at":"2026-07-05T00:40:25.641247+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2UYY7YCS2VT6IEI","created_at":"2026-07-05T00:40:25.641247+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2UYY7YC","created_at":"2026-07-05T00:40:25.641247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21247","citing_title":"Graph Navier Stokes Networks","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20248","citing_title":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21247","citing_title":"Graph Navier Stokes Networks","ref_index":86,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2UYY7YCS2VT6IEIZUW3NODERX","json":"https://pith.science/pith/M2UYY7YCS2VT6IEIZUW3NODERX.json","graph_json":"https://pith.science/api/pith-number/M2UYY7YCS2VT6IEIZUW3NODERX/graph.json","events_json":"https://pith.science/api/pith-number/M2UYY7YCS2VT6IEIZUW3NODERX/events.json","paper":"https://pith.science/paper/M2UYY7YC"},"agent_actions":{"view_html":"https://pith.science/pith/M2UYY7YCS2VT6IEIZUW3NODERX","download_json":"https://pith.science/pith/M2UYY7YCS2VT6IEIZUW3NODERX.json","view_paper":"https://pith.science/paper/M2UYY7YC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12223&json=true","fetch_graph":"https://pith.science/api/pith-number/M2UYY7YCS2VT6IEIZUW3NODERX/graph.json","fetch_events":"https://pith.science/api/pith-number/M2UYY7YCS2VT6IEIZUW3NODERX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2UYY7YCS2VT6IEIZUW3NODERX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2UYY7YCS2VT6IEIZUW3NODERX/action/storage_attestation","attest_author":"https://pith.science/pith/M2UYY7YCS2VT6IEIZUW3NODERX/action/author_attestation","sign_citation":"https://pith.science/pith/M2UYY7YCS2VT6IEIZUW3NODERX/action/citation_signature","submit_replication":"https://pith.science/pith/M2UYY7YCS2VT6IEIZUW3NODERX/action/replication_record"}},"created_at":"2026-07-05T00:40:25.641247+00:00","updated_at":"2026-07-05T00:40:25.641247+00:00"}