{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VINMT67PEPEA3Q6IIS6KZVHJ2B","short_pith_number":"pith:VINMT67P","schema_version":"1.0","canonical_sha256":"aa1ac9fbef23c80dc3c844bcacd4e9d0519294b2060e3a173221ad1ba1346fab","source":{"kind":"arxiv","id":"2201.11349","version":1},"attestation_state":"computed","paper":{"title":"Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"BinBin Hu, Chuan Shi, Hongrui Liu, Jun Zhou, Xiao Wang, Zhiqiang Zhang","submitted_at":"2022-01-27T07:12:27Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) have recently attracted vast interest and achieved state-of-the-art performance on graphs, but its success could typically hinge on careful training with amounts of expensive and time-consuming labeled data. To alleviate labeled data scarcity, self-training methods have been widely adopted on graphs by labeling high-confidence unlabeled nodes and then adding them to the training step. In this line, we empirically make a thorough study for current self-training methods on graphs. Surprisingly, we find that high-confidence unlabeled nodes are not always useful"},"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":"2201.11349","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T07:12:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f1f333a17d6383b55df99dd558ee3b1483eeb787541c9098f5029f1df5b13b6","abstract_canon_sha256":"2942582a2a0c9cf24f5d70ff36406ee9453e8839701af4975b97840180de661f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:01.586134Z","signature_b64":"XeQ2K83b4g8KSQMvqcogSWJmsdyCrVc572lEPhi5IDPxvg46onM9lFQw0aTsVq0ih9GieUSFkrkWu70NkPOFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa1ac9fbef23c80dc3c844bcacd4e9d0519294b2060e3a173221ad1ba1346fab","last_reissued_at":"2026-07-05T03:52:01.585738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:01.585738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"BinBin Hu, Chuan Shi, Hongrui Liu, Jun Zhou, Xiao Wang, Zhiqiang Zhang","submitted_at":"2022-01-27T07:12:27Z","abstract_excerpt":"Graph Convolutional Networks (GCNs) have recently attracted vast interest and achieved state-of-the-art performance on graphs, but its success could typically hinge on careful training with amounts of expensive and time-consuming labeled data. To alleviate labeled data scarcity, self-training methods have been widely adopted on graphs by labeling high-confidence unlabeled nodes and then adding them to the training step. In this line, we empirically make a thorough study for current self-training methods on graphs. Surprisingly, we find that high-confidence unlabeled nodes are not always useful"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11349","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/2201.11349/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":"2201.11349","created_at":"2026-07-05T03:52:01.585797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11349v1","created_at":"2026-07-05T03:52:01.585797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11349","created_at":"2026-07-05T03:52:01.585797+00:00"},{"alias_kind":"pith_short_12","alias_value":"VINMT67PEPEA","created_at":"2026-07-05T03:52:01.585797+00:00"},{"alias_kind":"pith_short_16","alias_value":"VINMT67PEPEA3Q6I","created_at":"2026-07-05T03:52:01.585797+00:00"},{"alias_kind":"pith_short_8","alias_value":"VINMT67P","created_at":"2026-07-05T03:52:01.585797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VINMT67PEPEA3Q6IIS6KZVHJ2B","json":"https://pith.science/pith/VINMT67PEPEA3Q6IIS6KZVHJ2B.json","graph_json":"https://pith.science/api/pith-number/VINMT67PEPEA3Q6IIS6KZVHJ2B/graph.json","events_json":"https://pith.science/api/pith-number/VINMT67PEPEA3Q6IIS6KZVHJ2B/events.json","paper":"https://pith.science/paper/VINMT67P"},"agent_actions":{"view_html":"https://pith.science/pith/VINMT67PEPEA3Q6IIS6KZVHJ2B","download_json":"https://pith.science/pith/VINMT67PEPEA3Q6IIS6KZVHJ2B.json","view_paper":"https://pith.science/paper/VINMT67P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11349&json=true","fetch_graph":"https://pith.science/api/pith-number/VINMT67PEPEA3Q6IIS6KZVHJ2B/graph.json","fetch_events":"https://pith.science/api/pith-number/VINMT67PEPEA3Q6IIS6KZVHJ2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VINMT67PEPEA3Q6IIS6KZVHJ2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VINMT67PEPEA3Q6IIS6KZVHJ2B/action/storage_attestation","attest_author":"https://pith.science/pith/VINMT67PEPEA3Q6IIS6KZVHJ2B/action/author_attestation","sign_citation":"https://pith.science/pith/VINMT67PEPEA3Q6IIS6KZVHJ2B/action/citation_signature","submit_replication":"https://pith.science/pith/VINMT67PEPEA3Q6IIS6KZVHJ2B/action/replication_record"}},"created_at":"2026-07-05T03:52:01.585797+00:00","updated_at":"2026-07-05T03:52:01.585797+00:00"}