{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XYKAG4CXAUN6ASHWGMEFPSQIIF","short_pith_number":"pith:XYKAG4CX","schema_version":"1.0","canonical_sha256":"be14037057051be048f6330857ca08415534e115faa42aab590d21b2a899ad2f","source":{"kind":"arxiv","id":"2306.01103","version":3},"attestation_state":"computed","paper":{"title":"Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Meng Liu, Shuiwang Ji, Shurui Gui, Xiner Li, Youzhi Luo","submitted_at":"2023-06-01T19:33:30Z","abstract_excerpt":"We tackle the problem of graph out-of-distribution (OOD) generalization. Existing graph OOD algorithms either rely on restricted assumptions or fail to exploit environment information in training data. In this work, we propose to simultaneously incorporate label and environment causal independence (LECI) to fully make use of label and environment information, thereby addressing the challenges faced by prior methods on identifying causal and invariant subgraphs. We further develop an adversarial training strategy to jointly optimize these two properties for causal subgraph discovery with theore"},"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":"2306.01103","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T19:33:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1b697e0453b69978ad8a7aa0d6f91dd89b0f248972fa0312677034e597a0d29","abstract_canon_sha256":"4c6d585a961f355c7eb7291d88aad92145c77e525381fce779a648dc45dffb8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:38.270569Z","signature_b64":"GfQUjD3ab13o/Vppfercw1M0wf8ZIqneHTXLCM23n5dvZxQLPNKYQsHIYaki+XXsgf7MsJ68dXOILHN8bJCgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be14037057051be048f6330857ca08415534e115faa42aab590d21b2a899ad2f","last_reissued_at":"2026-07-05T07:07:38.270096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:38.270096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Meng Liu, Shuiwang Ji, Shurui Gui, Xiner Li, Youzhi Luo","submitted_at":"2023-06-01T19:33:30Z","abstract_excerpt":"We tackle the problem of graph out-of-distribution (OOD) generalization. Existing graph OOD algorithms either rely on restricted assumptions or fail to exploit environment information in training data. In this work, we propose to simultaneously incorporate label and environment causal independence (LECI) to fully make use of label and environment information, thereby addressing the challenges faced by prior methods on identifying causal and invariant subgraphs. We further develop an adversarial training strategy to jointly optimize these two properties for causal subgraph discovery with theore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01103","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/2306.01103/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":"2306.01103","created_at":"2026-07-05T07:07:38.270156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01103v3","created_at":"2026-07-05T07:07:38.270156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01103","created_at":"2026-07-05T07:07:38.270156+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYKAG4CXAUN6","created_at":"2026-07-05T07:07:38.270156+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYKAG4CXAUN6ASHW","created_at":"2026-07-05T07:07:38.270156+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYKAG4CX","created_at":"2026-07-05T07:07:38.270156+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/XYKAG4CXAUN6ASHWGMEFPSQIIF","json":"https://pith.science/pith/XYKAG4CXAUN6ASHWGMEFPSQIIF.json","graph_json":"https://pith.science/api/pith-number/XYKAG4CXAUN6ASHWGMEFPSQIIF/graph.json","events_json":"https://pith.science/api/pith-number/XYKAG4CXAUN6ASHWGMEFPSQIIF/events.json","paper":"https://pith.science/paper/XYKAG4CX"},"agent_actions":{"view_html":"https://pith.science/pith/XYKAG4CXAUN6ASHWGMEFPSQIIF","download_json":"https://pith.science/pith/XYKAG4CXAUN6ASHWGMEFPSQIIF.json","view_paper":"https://pith.science/paper/XYKAG4CX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01103&json=true","fetch_graph":"https://pith.science/api/pith-number/XYKAG4CXAUN6ASHWGMEFPSQIIF/graph.json","fetch_events":"https://pith.science/api/pith-number/XYKAG4CXAUN6ASHWGMEFPSQIIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYKAG4CXAUN6ASHWGMEFPSQIIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYKAG4CXAUN6ASHWGMEFPSQIIF/action/storage_attestation","attest_author":"https://pith.science/pith/XYKAG4CXAUN6ASHWGMEFPSQIIF/action/author_attestation","sign_citation":"https://pith.science/pith/XYKAG4CXAUN6ASHWGMEFPSQIIF/action/citation_signature","submit_replication":"https://pith.science/pith/XYKAG4CXAUN6ASHWGMEFPSQIIF/action/replication_record"}},"created_at":"2026-07-05T07:07:38.270156+00:00","updated_at":"2026-07-05T07:07:38.270156+00:00"}