{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZFGUX3WVUAZ3SD5JDIUQRZ6HBS","short_pith_number":"pith:ZFGUX3WV","schema_version":"1.0","canonical_sha256":"c94d4beed5a033b90fa91a2908e7c70cbffa0fa6ba30969b2c2f1edaae62cbaa","source":{"kind":"arxiv","id":"1910.02684","version":4},"attestation_state":"computed","paper":{"title":"Effective Stabilized Self-Training on Few-Labeled Graph Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jieming Shi, Qing Li, Shengzhong Zhang, Zengfeng Huang, Ziang Zhou","submitted_at":"2019-10-07T09:21:49Z","abstract_excerpt":"Graph neural networks (GNNs) are designed for semi-supervised node classification on graphs where only a subset of nodes have class labels. However, under extreme cases when very few labels are available (e.g., 1 labeled node per class), GNNs suffer from severe performance degradation. Specifically, we observe that existing GNNs suffer from unstable training process on few-labeled graphs, resulting to inferior performance on node classification. Therefore, we propose an effective framework, Stabilized Self-Training (SST), which is applicable to existing GNNs to handle the scarcity of labeled d"},"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":"1910.02684","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-07T09:21:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e79b47ce9f1fd13840fe676437201258c28071be0c6635b1301964a81a240b31","abstract_canon_sha256":"7f88e353d2d2191729eb011d856885a27ea256fb123b711c9d194e1d37c151d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:00.590270Z","signature_b64":"5PQ7XZq5qBWFBQzGT4HxUenTTXfJIqUB8dB4Vp+tehAN9w4fNgfCzmvdLCWUjReJhoPExt3/uXM1W4rVo3dgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c94d4beed5a033b90fa91a2908e7c70cbffa0fa6ba30969b2c2f1edaae62cbaa","last_reissued_at":"2026-07-05T05:47:00.589772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:00.589772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Stabilized Self-Training on Few-Labeled Graph Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jieming Shi, Qing Li, Shengzhong Zhang, Zengfeng Huang, Ziang Zhou","submitted_at":"2019-10-07T09:21:49Z","abstract_excerpt":"Graph neural networks (GNNs) are designed for semi-supervised node classification on graphs where only a subset of nodes have class labels. However, under extreme cases when very few labels are available (e.g., 1 labeled node per class), GNNs suffer from severe performance degradation. Specifically, we observe that existing GNNs suffer from unstable training process on few-labeled graphs, resulting to inferior performance on node classification. Therefore, we propose an effective framework, Stabilized Self-Training (SST), which is applicable to existing GNNs to handle the scarcity of labeled d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02684","kind":"arxiv","version":4},"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/1910.02684/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":"1910.02684","created_at":"2026-07-05T05:47:00.589833+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.02684v4","created_at":"2026-07-05T05:47:00.589833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02684","created_at":"2026-07-05T05:47:00.589833+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFGUX3WVUAZ3","created_at":"2026-07-05T05:47:00.589833+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFGUX3WVUAZ3SD5J","created_at":"2026-07-05T05:47:00.589833+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFGUX3WV","created_at":"2026-07-05T05:47:00.589833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02451","citing_title":"Weak Supervision for Real World Graphs","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS","json":"https://pith.science/pith/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS.json","graph_json":"https://pith.science/api/pith-number/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS/graph.json","events_json":"https://pith.science/api/pith-number/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS/events.json","paper":"https://pith.science/paper/ZFGUX3WV"},"agent_actions":{"view_html":"https://pith.science/pith/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS","download_json":"https://pith.science/pith/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS.json","view_paper":"https://pith.science/paper/ZFGUX3WV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.02684&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS/action/storage_attestation","attest_author":"https://pith.science/pith/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS/action/author_attestation","sign_citation":"https://pith.science/pith/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS/action/citation_signature","submit_replication":"https://pith.science/pith/ZFGUX3WVUAZ3SD5JDIUQRZ6HBS/action/replication_record"}},"created_at":"2026-07-05T05:47:00.589833+00:00","updated_at":"2026-07-05T05:47:00.589833+00:00"}