{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GMAIATIH3ULZQ66RFFYGRTSOKU","short_pith_number":"pith:GMAIATIH","schema_version":"1.0","canonical_sha256":"3300804d07dd17987bd1297068ce4e551ab9b4ff48bdd9c0d48cdf80e4dca497","source":{"kind":"arxiv","id":"2503.03211","version":1},"attestation_state":"computed","paper":{"title":"NodeReg: Mitigating the Imbalance and Distribution Shift Effects in Semi-Supervised Node Classification via Norm Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingbo Zhou, Jun Xia, Shenzhi Yang, Xiaofang Zhang, Xingkai Yao","submitted_at":"2025-03-05T06:06:16Z","abstract_excerpt":"Aggregating information from neighboring nodes benefits graph neural networks (GNNs) in semi-supervised node classification tasks. Nevertheless, this mechanism also renders nodes susceptible to the influence of their neighbors. For instance, this will occur when the neighboring nodes are imbalanced or the neighboring nodes contain noise, which can even affect the GNN's ability to generalize out of distribution. We find that ensuring the consistency of the norm for node representations can significantly reduce the impact of these two issues on GNNs. To this end, we propose a regularized optimiz"},"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":"2503.03211","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T06:06:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cea2dbede7aa5de687eff626caaf0979a1d0af86f09134291b7bd40fb2220947","abstract_canon_sha256":"da18acf1ea2cbc0aaffeb62bf4dec27e5b255f78f41d4e3a2b5567e38e27adc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:41.375101Z","signature_b64":"CB+wb+d52gaia9BUUuUiUktUoapbBkwtrm0GjH418B8la2Qz5L2gtxT8sd8BkJoqOAarlTGNSf1lkt8LX2/bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3300804d07dd17987bd1297068ce4e551ab9b4ff48bdd9c0d48cdf80e4dca497","last_reissued_at":"2026-07-05T10:24:41.374311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:41.374311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NodeReg: Mitigating the Imbalance and Distribution Shift Effects in Semi-Supervised Node Classification via Norm Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jingbo Zhou, Jun Xia, Shenzhi Yang, Xiaofang Zhang, Xingkai Yao","submitted_at":"2025-03-05T06:06:16Z","abstract_excerpt":"Aggregating information from neighboring nodes benefits graph neural networks (GNNs) in semi-supervised node classification tasks. Nevertheless, this mechanism also renders nodes susceptible to the influence of their neighbors. For instance, this will occur when the neighboring nodes are imbalanced or the neighboring nodes contain noise, which can even affect the GNN's ability to generalize out of distribution. We find that ensuring the consistency of the norm for node representations can significantly reduce the impact of these two issues on GNNs. To this end, we propose a regularized optimiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03211","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/2503.03211/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":"2503.03211","created_at":"2026-07-05T10:24:41.374447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03211v1","created_at":"2026-07-05T10:24:41.374447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03211","created_at":"2026-07-05T10:24:41.374447+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMAIATIH3ULZ","created_at":"2026-07-05T10:24:41.374447+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMAIATIH3ULZQ66R","created_at":"2026-07-05T10:24:41.374447+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMAIATIH","created_at":"2026-07-05T10:24:41.374447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06682","citing_title":"Learning Robust Heterogeneous Graph Representations via Contrastive-Reconstruction under Sparse Semantics","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMAIATIH3ULZQ66RFFYGRTSOKU","json":"https://pith.science/pith/GMAIATIH3ULZQ66RFFYGRTSOKU.json","graph_json":"https://pith.science/api/pith-number/GMAIATIH3ULZQ66RFFYGRTSOKU/graph.json","events_json":"https://pith.science/api/pith-number/GMAIATIH3ULZQ66RFFYGRTSOKU/events.json","paper":"https://pith.science/paper/GMAIATIH"},"agent_actions":{"view_html":"https://pith.science/pith/GMAIATIH3ULZQ66RFFYGRTSOKU","download_json":"https://pith.science/pith/GMAIATIH3ULZQ66RFFYGRTSOKU.json","view_paper":"https://pith.science/paper/GMAIATIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03211&json=true","fetch_graph":"https://pith.science/api/pith-number/GMAIATIH3ULZQ66RFFYGRTSOKU/graph.json","fetch_events":"https://pith.science/api/pith-number/GMAIATIH3ULZQ66RFFYGRTSOKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMAIATIH3ULZQ66RFFYGRTSOKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMAIATIH3ULZQ66RFFYGRTSOKU/action/storage_attestation","attest_author":"https://pith.science/pith/GMAIATIH3ULZQ66RFFYGRTSOKU/action/author_attestation","sign_citation":"https://pith.science/pith/GMAIATIH3ULZQ66RFFYGRTSOKU/action/citation_signature","submit_replication":"https://pith.science/pith/GMAIATIH3ULZQ66RFFYGRTSOKU/action/replication_record"}},"created_at":"2026-07-05T10:24:41.374447+00:00","updated_at":"2026-07-05T10:24:41.374447+00:00"}