{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G5CZRWKUQA7ZDFWPEHXVUC3CJI","short_pith_number":"pith:G5CZRWKU","schema_version":"1.0","canonical_sha256":"374598d954803f9196cf21ef5a0b624a1e5a39a160f186a9c56979268da22c32","source":{"kind":"arxiv","id":"2202.02466","version":5},"attestation_state":"computed","paper":{"title":"Handling Distribution Shifts on Graphs: An Invariance Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Wipf, Hengrui Zhang, Junchi Yan, Qitian Wu","submitted_at":"2022-02-05T02:31:01Z","abstract_excerpt":"There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight. Nonetheless, current endeavors mostly focus on Euclidean data, and its formulation for graph-structured data is not clear and remains under-explored, given two-fold fundamental challenges: 1) the inter-connection among nodes in one graph, which induces non-IID generation of data points even under the same environment, and 2) the structural information in the input graph, which is also informative for prediction. In t"},"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":"2202.02466","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-05T02:31:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0043e0b947b20b49078ec9940669f882cb568a8e18b318775d17ec95d8a37844","abstract_canon_sha256":"dbddb8eb7e4af718adb7147ed9c132d8f6adcf344a7def2de0166840c3178dc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:01.503707Z","signature_b64":"CMJMXhUfn39RtHwwarj6U8qlsAbT9VPH9FXcFmHJcI4B393kTl5mIIgNoIC/c1Y6j4iG8+NWJS6Rygl69U65DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"374598d954803f9196cf21ef5a0b624a1e5a39a160f186a9c56979268da22c32","last_reissued_at":"2026-07-05T08:56:01.503286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:01.503286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Handling Distribution Shifts on Graphs: An Invariance Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Wipf, Hengrui Zhang, Junchi Yan, Qitian Wu","submitted_at":"2022-02-05T02:31:01Z","abstract_excerpt":"There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight. Nonetheless, current endeavors mostly focus on Euclidean data, and its formulation for graph-structured data is not clear and remains under-explored, given two-fold fundamental challenges: 1) the inter-connection among nodes in one graph, which induces non-IID generation of data points even under the same environment, and 2) the structural information in the input graph, which is also informative for prediction. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02466","kind":"arxiv","version":5},"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/2202.02466/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":"2202.02466","created_at":"2026-07-05T08:56:01.503345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02466v5","created_at":"2026-07-05T08:56:01.503345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02466","created_at":"2026-07-05T08:56:01.503345+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5CZRWKUQA7Z","created_at":"2026-07-05T08:56:01.503345+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5CZRWKUQA7ZDFWP","created_at":"2026-07-05T08:56:01.503345+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5CZRWKU","created_at":"2026-07-05T08:56:01.503345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18579","citing_title":"S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18579","citing_title":"S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5CZRWKUQA7ZDFWPEHXVUC3CJI","json":"https://pith.science/pith/G5CZRWKUQA7ZDFWPEHXVUC3CJI.json","graph_json":"https://pith.science/api/pith-number/G5CZRWKUQA7ZDFWPEHXVUC3CJI/graph.json","events_json":"https://pith.science/api/pith-number/G5CZRWKUQA7ZDFWPEHXVUC3CJI/events.json","paper":"https://pith.science/paper/G5CZRWKU"},"agent_actions":{"view_html":"https://pith.science/pith/G5CZRWKUQA7ZDFWPEHXVUC3CJI","download_json":"https://pith.science/pith/G5CZRWKUQA7ZDFWPEHXVUC3CJI.json","view_paper":"https://pith.science/paper/G5CZRWKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02466&json=true","fetch_graph":"https://pith.science/api/pith-number/G5CZRWKUQA7ZDFWPEHXVUC3CJI/graph.json","fetch_events":"https://pith.science/api/pith-number/G5CZRWKUQA7ZDFWPEHXVUC3CJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5CZRWKUQA7ZDFWPEHXVUC3CJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5CZRWKUQA7ZDFWPEHXVUC3CJI/action/storage_attestation","attest_author":"https://pith.science/pith/G5CZRWKUQA7ZDFWPEHXVUC3CJI/action/author_attestation","sign_citation":"https://pith.science/pith/G5CZRWKUQA7ZDFWPEHXVUC3CJI/action/citation_signature","submit_replication":"https://pith.science/pith/G5CZRWKUQA7ZDFWPEHXVUC3CJI/action/replication_record"}},"created_at":"2026-07-05T08:56:01.503345+00:00","updated_at":"2026-07-05T08:56:01.503345+00:00"}