{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IMRFGE74UZAOAAFHK4OZ63MLCO","short_pith_number":"pith:IMRFGE74","schema_version":"1.0","canonical_sha256":"43225313fca640e000a7571d9f6d8b13b771015ab3000e0988afe8e9551759da","source":{"kind":"arxiv","id":"2304.14635","version":1},"attestation_state":"computed","paper":{"title":"Imbalanced Node Classification Beyond Homophilic Assumption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guangtao Wang, Hongzhi Yin, Jie Liu, Mengting He, Nguyen Quoc Viet Hung, Xuequn Shang","submitted_at":"2023-04-28T05:33:19Z","abstract_excerpt":"Imbalanced node classification widely exists in real-world networks where graph neural networks (GNNs) are usually highly inclined to majority classes and suffer from severe performance degradation on classifying minority class nodes. Various imbalanced node classification methods have been proposed recently which construct synthetic nodes and edges w.r.t. minority classes to balance the label and topology distribution. However, they are all based on the homophilic assumption that nodes of the same label tend to connect despite the wide existence of heterophilic edges in real-world graphs. Thu"},"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":"2304.14635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-28T05:33:19Z","cross_cats_sorted":[],"title_canon_sha256":"50b535cf75fddef4d145c5bb7ec477a711f451fe9adcfa671b4d84f90419343e","abstract_canon_sha256":"dbc25fe83975f7635e115b65c7f792a242d1b4bff51c4c30b3425e7df8d8386f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:19.351845Z","signature_b64":"R2uxXPS3theHekmDNzGvVwq5Mi/B9byhmTlWCbo1QO52m4MaaIde+Xdp16Gx+XnNgwTBqOCQ+qyUI9BKRlEsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43225313fca640e000a7571d9f6d8b13b771015ab3000e0988afe8e9551759da","last_reissued_at":"2026-07-05T06:05:19.351466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:19.351466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imbalanced Node Classification Beyond Homophilic Assumption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guangtao Wang, Hongzhi Yin, Jie Liu, Mengting He, Nguyen Quoc Viet Hung, Xuequn Shang","submitted_at":"2023-04-28T05:33:19Z","abstract_excerpt":"Imbalanced node classification widely exists in real-world networks where graph neural networks (GNNs) are usually highly inclined to majority classes and suffer from severe performance degradation on classifying minority class nodes. Various imbalanced node classification methods have been proposed recently which construct synthetic nodes and edges w.r.t. minority classes to balance the label and topology distribution. However, they are all based on the homophilic assumption that nodes of the same label tend to connect despite the wide existence of heterophilic edges in real-world graphs. Thu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14635","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/2304.14635/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":"2304.14635","created_at":"2026-07-05T06:05:19.351537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14635v1","created_at":"2026-07-05T06:05:19.351537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14635","created_at":"2026-07-05T06:05:19.351537+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMRFGE74UZAO","created_at":"2026-07-05T06:05:19.351537+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMRFGE74UZAOAAFH","created_at":"2026-07-05T06:05:19.351537+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMRFGE74","created_at":"2026-07-05T06:05:19.351537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01124","citing_title":"Towards Propagation-aware Representation Learning for Supervised Social Media Graph Analytics","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMRFGE74UZAOAAFHK4OZ63MLCO","json":"https://pith.science/pith/IMRFGE74UZAOAAFHK4OZ63MLCO.json","graph_json":"https://pith.science/api/pith-number/IMRFGE74UZAOAAFHK4OZ63MLCO/graph.json","events_json":"https://pith.science/api/pith-number/IMRFGE74UZAOAAFHK4OZ63MLCO/events.json","paper":"https://pith.science/paper/IMRFGE74"},"agent_actions":{"view_html":"https://pith.science/pith/IMRFGE74UZAOAAFHK4OZ63MLCO","download_json":"https://pith.science/pith/IMRFGE74UZAOAAFHK4OZ63MLCO.json","view_paper":"https://pith.science/paper/IMRFGE74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14635&json=true","fetch_graph":"https://pith.science/api/pith-number/IMRFGE74UZAOAAFHK4OZ63MLCO/graph.json","fetch_events":"https://pith.science/api/pith-number/IMRFGE74UZAOAAFHK4OZ63MLCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMRFGE74UZAOAAFHK4OZ63MLCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMRFGE74UZAOAAFHK4OZ63MLCO/action/storage_attestation","attest_author":"https://pith.science/pith/IMRFGE74UZAOAAFHK4OZ63MLCO/action/author_attestation","sign_citation":"https://pith.science/pith/IMRFGE74UZAOAAFHK4OZ63MLCO/action/citation_signature","submit_replication":"https://pith.science/pith/IMRFGE74UZAOAAFHK4OZ63MLCO/action/replication_record"}},"created_at":"2026-07-05T06:05:19.351537+00:00","updated_at":"2026-07-05T06:05:19.351537+00:00"}