{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BKDKAARZDZZ7YE4RPAJD4CELMG","short_pith_number":"pith:BKDKAARZ","schema_version":"1.0","canonical_sha256":"0a86a002391e73fc139178123e088b61a508bafd468e2e3fa17862ed28618062","source":{"kind":"arxiv","id":"2202.05441","version":3},"attestation_state":"computed","paper":{"title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Binghui Xie, Bo Han, Han Yang, James Cheng, Kaili Ma, Tongliang Liu, Yatao Bian, Yonggang Zhang, Yongqiang Chen","submitted_at":"2022-02-11T04:38:39Z","abstract_excerpt":"Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e.g., images), studies on graph data are still limited. Different from images, the complex nature of graphs poses unique challenges to adopting the invariance principle. In particular, distribution shifts on graphs can appear in a variety of forms such as attributes and structures, making it difficult to identify the invariance. Moreover, domain or environment partitions, which are often required by OOD methods on Euclidean data, could be highly expensive to obtain for graph"},"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":"2202.05441","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T04:38:39Z","cross_cats_sorted":[],"title_canon_sha256":"b85e88ac772d00c7f7eff1acd96dc9bea3e018896e70df192e66af74f1be4b36","abstract_canon_sha256":"ba623fdc91e6140f007f0fced0c089e59ac8a0b8cf2eb0a09e170b51144f9860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:02.951885Z","signature_b64":"NvZDi2/6agvf3RVFW4LTC1F3lq4iPYD3lhcxzW+G+Vj6y9dv7PRIDsHHqouAjKHUx4Gq0X7nniyGLtJmPJXlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a86a002391e73fc139178123e088b61a508bafd468e2e3fa17862ed28618062","last_reissued_at":"2026-07-05T05:05:02.951479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:02.951479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Binghui Xie, Bo Han, Han Yang, James Cheng, Kaili Ma, Tongliang Liu, Yatao Bian, Yonggang Zhang, Yongqiang Chen","submitted_at":"2022-02-11T04:38:39Z","abstract_excerpt":"Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e.g., images), studies on graph data are still limited. Different from images, the complex nature of graphs poses unique challenges to adopting the invariance principle. In particular, distribution shifts on graphs can appear in a variety of forms such as attributes and structures, making it difficult to identify the invariance. Moreover, domain or environment partitions, which are often required by OOD methods on Euclidean data, could be highly expensive to obtain for graph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05441","kind":"arxiv","version":3},"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/2202.05441/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":"2202.05441","created_at":"2026-07-05T05:05:02.951535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.05441v3","created_at":"2026-07-05T05:05:02.951535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05441","created_at":"2026-07-05T05:05:02.951535+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKDKAARZDZZ7","created_at":"2026-07-05T05:05:02.951535+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKDKAARZDZZ7YE4R","created_at":"2026-07-05T05:05:02.951535+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKDKAARZ","created_at":"2026-07-05T05:05:02.951535+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/BKDKAARZDZZ7YE4RPAJD4CELMG","json":"https://pith.science/pith/BKDKAARZDZZ7YE4RPAJD4CELMG.json","graph_json":"https://pith.science/api/pith-number/BKDKAARZDZZ7YE4RPAJD4CELMG/graph.json","events_json":"https://pith.science/api/pith-number/BKDKAARZDZZ7YE4RPAJD4CELMG/events.json","paper":"https://pith.science/paper/BKDKAARZ"},"agent_actions":{"view_html":"https://pith.science/pith/BKDKAARZDZZ7YE4RPAJD4CELMG","download_json":"https://pith.science/pith/BKDKAARZDZZ7YE4RPAJD4CELMG.json","view_paper":"https://pith.science/paper/BKDKAARZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.05441&json=true","fetch_graph":"https://pith.science/api/pith-number/BKDKAARZDZZ7YE4RPAJD4CELMG/graph.json","fetch_events":"https://pith.science/api/pith-number/BKDKAARZDZZ7YE4RPAJD4CELMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKDKAARZDZZ7YE4RPAJD4CELMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKDKAARZDZZ7YE4RPAJD4CELMG/action/storage_attestation","attest_author":"https://pith.science/pith/BKDKAARZDZZ7YE4RPAJD4CELMG/action/author_attestation","sign_citation":"https://pith.science/pith/BKDKAARZDZZ7YE4RPAJD4CELMG/action/citation_signature","submit_replication":"https://pith.science/pith/BKDKAARZDZZ7YE4RPAJD4CELMG/action/replication_record"}},"created_at":"2026-07-05T05:05:02.951535+00:00","updated_at":"2026-07-05T05:05:02.951535+00:00"}