{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KUTWIVS4QPZA27GYAMCLH3XL7I","short_pith_number":"pith:KUTWIVS4","schema_version":"1.0","canonical_sha256":"552764565c83f20d7cd80304b3eeebfa3a92b78893996d3d2240d5cd3ac4e0d4","source":{"kind":"arxiv","id":"2411.13821","version":2},"attestation_state":"computed","paper":{"title":"Heterophilic Graph Neural Networks Optimization with Causal Message-passing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Botao Wang, Fugee Tsung, Heng Chang, Jia Li, Keli Zhang","submitted_at":"2024-11-21T03:59:07Z","abstract_excerpt":"In this work, we discover that causal inference provides a promising approach to capture heterophilic message-passing in Graph Neural Network (GNN). By leveraging cause-effect analysis, we can discern heterophilic edges based on asymmetric node dependency. The learned causal structure offers more accurate relationships among nodes. To reduce the computational complexity, we introduce intervention-based causal inference in graph learning. We first simplify causal analysis on graphs by formulating it as a structural learning model and define the optimization problem within the Bayesian scheme. W"},"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":"2411.13821","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T03:59:07Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"870c27fc7aa0144a1fb59930660194883b3f29d09aaffc4801aa861dfcf31637","abstract_canon_sha256":"208a788a2d1627cb6d7044288d0b9ec20c557b9e823d08533be1d04e066c65f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:03.957542Z","signature_b64":"mpGvpL74e0qGCzc8X6HgMMTGBdEyDTo09vYX7cEEEmQP8xOs42Hleo4I4+LL2STON/lUwNWN2AbiTL9qVwGfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"552764565c83f20d7cd80304b3eeebfa3a92b78893996d3d2240d5cd3ac4e0d4","last_reissued_at":"2026-07-05T09:41:03.957064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:03.957064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterophilic Graph Neural Networks Optimization with Causal Message-passing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Botao Wang, Fugee Tsung, Heng Chang, Jia Li, Keli Zhang","submitted_at":"2024-11-21T03:59:07Z","abstract_excerpt":"In this work, we discover that causal inference provides a promising approach to capture heterophilic message-passing in Graph Neural Network (GNN). By leveraging cause-effect analysis, we can discern heterophilic edges based on asymmetric node dependency. The learned causal structure offers more accurate relationships among nodes. To reduce the computational complexity, we introduce intervention-based causal inference in graph learning. We first simplify causal analysis on graphs by formulating it as a structural learning model and define the optimization problem within the Bayesian scheme. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13821","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/2411.13821/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":"2411.13821","created_at":"2026-07-05T09:41:03.957122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13821v2","created_at":"2026-07-05T09:41:03.957122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13821","created_at":"2026-07-05T09:41:03.957122+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUTWIVS4QPZA","created_at":"2026-07-05T09:41:03.957122+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUTWIVS4QPZA27GY","created_at":"2026-07-05T09:41:03.957122+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUTWIVS4","created_at":"2026-07-05T09:41:03.957122+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/KUTWIVS4QPZA27GYAMCLH3XL7I","json":"https://pith.science/pith/KUTWIVS4QPZA27GYAMCLH3XL7I.json","graph_json":"https://pith.science/api/pith-number/KUTWIVS4QPZA27GYAMCLH3XL7I/graph.json","events_json":"https://pith.science/api/pith-number/KUTWIVS4QPZA27GYAMCLH3XL7I/events.json","paper":"https://pith.science/paper/KUTWIVS4"},"agent_actions":{"view_html":"https://pith.science/pith/KUTWIVS4QPZA27GYAMCLH3XL7I","download_json":"https://pith.science/pith/KUTWIVS4QPZA27GYAMCLH3XL7I.json","view_paper":"https://pith.science/paper/KUTWIVS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13821&json=true","fetch_graph":"https://pith.science/api/pith-number/KUTWIVS4QPZA27GYAMCLH3XL7I/graph.json","fetch_events":"https://pith.science/api/pith-number/KUTWIVS4QPZA27GYAMCLH3XL7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUTWIVS4QPZA27GYAMCLH3XL7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUTWIVS4QPZA27GYAMCLH3XL7I/action/storage_attestation","attest_author":"https://pith.science/pith/KUTWIVS4QPZA27GYAMCLH3XL7I/action/author_attestation","sign_citation":"https://pith.science/pith/KUTWIVS4QPZA27GYAMCLH3XL7I/action/citation_signature","submit_replication":"https://pith.science/pith/KUTWIVS4QPZA27GYAMCLH3XL7I/action/replication_record"}},"created_at":"2026-07-05T09:41:03.957122+00:00","updated_at":"2026-07-05T09:41:03.957122+00:00"}