{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6IQ4TFSYOGLQK3ORZZZPAXIX6U","short_pith_number":"pith:6IQ4TFSY","schema_version":"1.0","canonical_sha256":"f221c996587197056dd1ce72f05d17f527684da12e392153fd6ec2c182f345c6","source":{"kind":"arxiv","id":"2502.08105","version":1},"attestation_state":"computed","paper":{"title":"Out-of-Distribution Detection on Graphs: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changqin Huang, Ming Li, Shirui Pan, Tingyi Cai, Yixin Liu, Yunliang Jiang","submitted_at":"2025-02-12T04:07:12Z","abstract_excerpt":"Graph machine learning has witnessed rapid growth, driving advancements across diverse domains. However, the in-distribution assumption, where training and testing data share the same distribution, often breaks in real-world scenarios, leading to degraded model performance under distribution shifts. This challenge has catalyzed interest in graph out-of-distribution (GOOD) detection, which focuses on identifying graph data that deviates from the distribution seen during training, thereby enhancing model robustness. In this paper, we provide a rigorous definition of GOOD detection and systematic"},"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":"2502.08105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T04:07:12Z","cross_cats_sorted":[],"title_canon_sha256":"adfebbf0471f2241058a3b086e515b4b638263b9d915629d9a9da0173bc369c3","abstract_canon_sha256":"0676b59b6e66b94b148e8f5e12ceaf29a98d66175065cfa683ac6c00a4a02d69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:15.431760Z","signature_b64":"lk6Vp0F3Mb0tV9XKtCdFPFnzQdtI0Voj8opYrQxHtu+7BILruyo9LRBNM5rb1qGG05r77vAjjGEHo6O8K5sgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f221c996587197056dd1ce72f05d17f527684da12e392153fd6ec2c182f345c6","last_reissued_at":"2026-07-05T10:13:15.431201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:15.431201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out-of-Distribution Detection on Graphs: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changqin Huang, Ming Li, Shirui Pan, Tingyi Cai, Yixin Liu, Yunliang Jiang","submitted_at":"2025-02-12T04:07:12Z","abstract_excerpt":"Graph machine learning has witnessed rapid growth, driving advancements across diverse domains. However, the in-distribution assumption, where training and testing data share the same distribution, often breaks in real-world scenarios, leading to degraded model performance under distribution shifts. This challenge has catalyzed interest in graph out-of-distribution (GOOD) detection, which focuses on identifying graph data that deviates from the distribution seen during training, thereby enhancing model robustness. In this paper, we provide a rigorous definition of GOOD detection and systematic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08105","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/2502.08105/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":"2502.08105","created_at":"2026-07-05T10:13:15.431263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08105v1","created_at":"2026-07-05T10:13:15.431263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08105","created_at":"2026-07-05T10:13:15.431263+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IQ4TFSYOGLQ","created_at":"2026-07-05T10:13:15.431263+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IQ4TFSYOGLQK3OR","created_at":"2026-07-05T10:13:15.431263+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IQ4TFSY","created_at":"2026-07-05T10:13:15.431263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.32016","citing_title":"FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20032","citing_title":"CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06050","citing_title":"When Brain Networks Travel: Learning Beyond Site","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6IQ4TFSYOGLQK3ORZZZPAXIX6U","json":"https://pith.science/pith/6IQ4TFSYOGLQK3ORZZZPAXIX6U.json","graph_json":"https://pith.science/api/pith-number/6IQ4TFSYOGLQK3ORZZZPAXIX6U/graph.json","events_json":"https://pith.science/api/pith-number/6IQ4TFSYOGLQK3ORZZZPAXIX6U/events.json","paper":"https://pith.science/paper/6IQ4TFSY"},"agent_actions":{"view_html":"https://pith.science/pith/6IQ4TFSYOGLQK3ORZZZPAXIX6U","download_json":"https://pith.science/pith/6IQ4TFSYOGLQK3ORZZZPAXIX6U.json","view_paper":"https://pith.science/paper/6IQ4TFSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08105&json=true","fetch_graph":"https://pith.science/api/pith-number/6IQ4TFSYOGLQK3ORZZZPAXIX6U/graph.json","fetch_events":"https://pith.science/api/pith-number/6IQ4TFSYOGLQK3ORZZZPAXIX6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IQ4TFSYOGLQK3ORZZZPAXIX6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IQ4TFSYOGLQK3ORZZZPAXIX6U/action/storage_attestation","attest_author":"https://pith.science/pith/6IQ4TFSYOGLQK3ORZZZPAXIX6U/action/author_attestation","sign_citation":"https://pith.science/pith/6IQ4TFSYOGLQK3ORZZZPAXIX6U/action/citation_signature","submit_replication":"https://pith.science/pith/6IQ4TFSYOGLQK3ORZZZPAXIX6U/action/replication_record"}},"created_at":"2026-07-05T10:13:15.431263+00:00","updated_at":"2026-07-05T10:13:15.431263+00:00"}