{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DH4RQDORBU4KDNBW2ZLOVQZJLS","short_pith_number":"pith:DH4RQDOR","schema_version":"1.0","canonical_sha256":"19f9180dd10d38a1b436d656eac3295cb25aa4bfe2b7d8797200450d193f6d54","source":{"kind":"arxiv","id":"2202.07987","version":2},"attestation_state":"computed","paper":{"title":"Out-Of-Distribution Generalization on Graphs: A Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoyang Li, Wenwu Zhu, Xin Wang, Ziwei Zhang","submitted_at":"2022-02-16T10:59:06Z","abstract_excerpt":"Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution hypothesis, i.e., testing and training graph data are identically distributed. However, this in-distribution hypothesis can hardly be satisfied in many real-world graph scenarios where the model performance substantially degrades when there exist distribution shifts between testing and training graph data. To solve this critical problem, out-of-distribution (OOD) generalization on graphs"},"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":"2202.07987","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-16T10:59:06Z","cross_cats_sorted":[],"title_canon_sha256":"2bf0ba3e4da52b5545747255c1b3a1f8bc182fab46912fa9240470f2db8569ab","abstract_canon_sha256":"6598616653365162bccedd3e22b2136162e4273c956ce09b6f36c9f0f7c0cab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:00.953021Z","signature_b64":"bR6Nt/v53YGSD4AmQtQ5qDWGqZZPgnWhpfFUjF1whXJqaihwN4ZjzKTH9FWC6WPciJFNh9O5zLYaFQbaiIhYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19f9180dd10d38a1b436d656eac3295cb25aa4bfe2b7d8797200450d193f6d54","last_reissued_at":"2026-07-05T05:29:00.952565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:00.952565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out-Of-Distribution Generalization on Graphs: A Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoyang Li, Wenwu Zhu, Xin Wang, Ziwei Zhang","submitted_at":"2022-02-16T10:59:06Z","abstract_excerpt":"Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution hypothesis, i.e., testing and training graph data are identically distributed. However, this in-distribution hypothesis can hardly be satisfied in many real-world graph scenarios where the model performance substantially degrades when there exist distribution shifts between testing and training graph data. To solve this critical problem, out-of-distribution (OOD) generalization on graphs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07987","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/2202.07987/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":"2202.07987","created_at":"2026-07-05T05:29:00.952618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07987v2","created_at":"2026-07-05T05:29:00.952618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07987","created_at":"2026-07-05T05:29:00.952618+00:00"},{"alias_kind":"pith_short_12","alias_value":"DH4RQDORBU4K","created_at":"2026-07-05T05:29:00.952618+00:00"},{"alias_kind":"pith_short_16","alias_value":"DH4RQDORBU4KDNBW","created_at":"2026-07-05T05:29:00.952618+00:00"},{"alias_kind":"pith_short_8","alias_value":"DH4RQDOR","created_at":"2026-07-05T05:29:00.952618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08404","citing_title":"Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23514","citing_title":"Probabilistic Graphical Model using Graph Neural Networks for Bayesian Inversion of Discrete Structural Component States","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DH4RQDORBU4KDNBW2ZLOVQZJLS","json":"https://pith.science/pith/DH4RQDORBU4KDNBW2ZLOVQZJLS.json","graph_json":"https://pith.science/api/pith-number/DH4RQDORBU4KDNBW2ZLOVQZJLS/graph.json","events_json":"https://pith.science/api/pith-number/DH4RQDORBU4KDNBW2ZLOVQZJLS/events.json","paper":"https://pith.science/paper/DH4RQDOR"},"agent_actions":{"view_html":"https://pith.science/pith/DH4RQDORBU4KDNBW2ZLOVQZJLS","download_json":"https://pith.science/pith/DH4RQDORBU4KDNBW2ZLOVQZJLS.json","view_paper":"https://pith.science/paper/DH4RQDOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07987&json=true","fetch_graph":"https://pith.science/api/pith-number/DH4RQDORBU4KDNBW2ZLOVQZJLS/graph.json","fetch_events":"https://pith.science/api/pith-number/DH4RQDORBU4KDNBW2ZLOVQZJLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DH4RQDORBU4KDNBW2ZLOVQZJLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DH4RQDORBU4KDNBW2ZLOVQZJLS/action/storage_attestation","attest_author":"https://pith.science/pith/DH4RQDORBU4KDNBW2ZLOVQZJLS/action/author_attestation","sign_citation":"https://pith.science/pith/DH4RQDORBU4KDNBW2ZLOVQZJLS/action/citation_signature","submit_replication":"https://pith.science/pith/DH4RQDORBU4KDNBW2ZLOVQZJLS/action/replication_record"}},"created_at":"2026-07-05T05:29:00.952618+00:00","updated_at":"2026-07-05T05:29:00.952618+00:00"}