{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T4RMZTTKHLLO5FTYUEV3WBVNJG","short_pith_number":"pith:T4RMZTTK","schema_version":"1.0","canonical_sha256":"9f22ccce6a3ad6ee9678a12bbb06ad49b9271d57c150b659bd7ed625197fe7cd","source":{"kind":"arxiv","id":"2112.04319","version":2},"attestation_state":"computed","paper":{"title":"SCR: Training Graph Neural Networks with Consistency Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.SI","authors_text":"Chenhui Zhang, Feng He, Hongyun Cai, Jie Tang, Wenzheng Feng, Xu Cheng, Yufei He, Yukuo Cen, Yuxiao Dong, Zhenyu Hou","submitted_at":"2021-12-08T14:51:30Z","abstract_excerpt":"We present the SCR framework for enhancing the training of graph neural networks (GNNs) with consistency regularization. Regularization is a set of strategies used in Machine Learning to reduce overfitting and improve the generalization ability. However, it is unclear how to best design the generalization strategies in GNNs, as it works in a semi-supervised setting for graph data. The major challenge lies in how to efficiently balance the trade-off between the error from the labeled data and that from the unlabeled data. SCR is a simple yet general framework in which we introduce two strategie"},"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":"2112.04319","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2021-12-08T14:51:30Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2cc9d26c59323ebb0fb04c33b4b3c9c7d2ff921dc3069d0f3ed86bf4002010d4","abstract_canon_sha256":"8ea62caf8c990a44921cbb28b8840d1c848a7cf0fb1ddb00f793713e02902f84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:11.638792Z","signature_b64":"8zY55MMM1rfwZMtcapPegWaI9b3LFD6vR+IJQnX32q3YM0TispiaKDB/lguhOz1YyyelmTFctDP0eJD7BCy/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f22ccce6a3ad6ee9678a12bbb06ad49b9271d57c150b659bd7ed625197fe7cd","last_reissued_at":"2026-07-05T04:31:11.638267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:11.638267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCR: Training Graph Neural Networks with Consistency Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.SI","authors_text":"Chenhui Zhang, Feng He, Hongyun Cai, Jie Tang, Wenzheng Feng, Xu Cheng, Yufei He, Yukuo Cen, Yuxiao Dong, Zhenyu Hou","submitted_at":"2021-12-08T14:51:30Z","abstract_excerpt":"We present the SCR framework for enhancing the training of graph neural networks (GNNs) with consistency regularization. Regularization is a set of strategies used in Machine Learning to reduce overfitting and improve the generalization ability. However, it is unclear how to best design the generalization strategies in GNNs, as it works in a semi-supervised setting for graph data. The major challenge lies in how to efficiently balance the trade-off between the error from the labeled data and that from the unlabeled data. SCR is a simple yet general framework in which we introduce two strategie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04319","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/2112.04319/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":"2112.04319","created_at":"2026-07-05T04:31:11.638344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04319v2","created_at":"2026-07-05T04:31:11.638344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04319","created_at":"2026-07-05T04:31:11.638344+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4RMZTTKHLLO","created_at":"2026-07-05T04:31:11.638344+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4RMZTTKHLLO5FTY","created_at":"2026-07-05T04:31:11.638344+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4RMZTTK","created_at":"2026-07-05T04:31:11.638344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.00318","citing_title":"Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4RMZTTKHLLO5FTYUEV3WBVNJG","json":"https://pith.science/pith/T4RMZTTKHLLO5FTYUEV3WBVNJG.json","graph_json":"https://pith.science/api/pith-number/T4RMZTTKHLLO5FTYUEV3WBVNJG/graph.json","events_json":"https://pith.science/api/pith-number/T4RMZTTKHLLO5FTYUEV3WBVNJG/events.json","paper":"https://pith.science/paper/T4RMZTTK"},"agent_actions":{"view_html":"https://pith.science/pith/T4RMZTTKHLLO5FTYUEV3WBVNJG","download_json":"https://pith.science/pith/T4RMZTTKHLLO5FTYUEV3WBVNJG.json","view_paper":"https://pith.science/paper/T4RMZTTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04319&json=true","fetch_graph":"https://pith.science/api/pith-number/T4RMZTTKHLLO5FTYUEV3WBVNJG/graph.json","fetch_events":"https://pith.science/api/pith-number/T4RMZTTKHLLO5FTYUEV3WBVNJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4RMZTTKHLLO5FTYUEV3WBVNJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4RMZTTKHLLO5FTYUEV3WBVNJG/action/storage_attestation","attest_author":"https://pith.science/pith/T4RMZTTKHLLO5FTYUEV3WBVNJG/action/author_attestation","sign_citation":"https://pith.science/pith/T4RMZTTKHLLO5FTYUEV3WBVNJG/action/citation_signature","submit_replication":"https://pith.science/pith/T4RMZTTKHLLO5FTYUEV3WBVNJG/action/replication_record"}},"created_at":"2026-07-05T04:31:11.638344+00:00","updated_at":"2026-07-05T04:31:11.638344+00:00"}