{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7QBJS6RMOHJY3R2JPRY4WYH4JS","short_pith_number":"pith:7QBJS6RM","schema_version":"1.0","canonical_sha256":"fc02997a2c71d38dc7497c71cb60fc4c813b0ce8bbb7a46227ca81b2b6dd1291","source":{"kind":"arxiv","id":"2204.04879","version":1},"attestation_state":"computed","paper":{"title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alice Oh, Dongkwan Kim","submitted_at":"2022-04-11T05:45:09Z","abstract_excerpt":"Attention mechanism in graph neural networks is designed to assign larger weights to important neighbor nodes for better representation. However, what graph attention learns is not understood well, particularly when graphs are noisy. In this paper, we propose a self-supervised graph attention network (SuperGAT), an improved graph attention model for noisy graphs. Specifically, we exploit two attention forms compatible with a self-supervised task to predict edges, whose presence and absence contain the inherent information about the importance of the relationships between nodes. By encoding edg"},"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":"2204.04879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-11T05:45:09Z","cross_cats_sorted":["cs.AI","cs.SI","stat.ML"],"title_canon_sha256":"a1e7652e8f4ed32235a8c32e9537aa1ffb9d930066e75faed0369401e6aa8732","abstract_canon_sha256":"ec3aaa4a80fa2e8060d3a002d828251b39e92f731cd0b58c5a326f3d0c28becf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:15.119738Z","signature_b64":"9QB11JovAwyAB8wAOKZFC9OeHY+sLZI1zafP/Ktof3/56uk0OHAjSUMhIOG47uJZKMdEfr1nSCaQdNZOyIjFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc02997a2c71d38dc7497c71cb60fc4c813b0ce8bbb7a46227ca81b2b6dd1291","last_reissued_at":"2026-07-05T04:13:15.119265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:15.119265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alice Oh, Dongkwan Kim","submitted_at":"2022-04-11T05:45:09Z","abstract_excerpt":"Attention mechanism in graph neural networks is designed to assign larger weights to important neighbor nodes for better representation. However, what graph attention learns is not understood well, particularly when graphs are noisy. In this paper, we propose a self-supervised graph attention network (SuperGAT), an improved graph attention model for noisy graphs. Specifically, we exploit two attention forms compatible with a self-supervised task to predict edges, whose presence and absence contain the inherent information about the importance of the relationships between nodes. By encoding edg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04879","kind":"arxiv","version":1},"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/2204.04879/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":"2204.04879","created_at":"2026-07-05T04:13:15.119325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.04879v1","created_at":"2026-07-05T04:13:15.119325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04879","created_at":"2026-07-05T04:13:15.119325+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QBJS6RMOHJY","created_at":"2026-07-05T04:13:15.119325+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QBJS6RMOHJY3R2J","created_at":"2026-07-05T04:13:15.119325+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QBJS6RM","created_at":"2026-07-05T04:13:15.119325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07383","citing_title":"SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objective","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07383","citing_title":"SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objective","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20082","citing_title":"Concept Graph Convolutions: Message Passing in the Concept Space","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QBJS6RMOHJY3R2JPRY4WYH4JS","json":"https://pith.science/pith/7QBJS6RMOHJY3R2JPRY4WYH4JS.json","graph_json":"https://pith.science/api/pith-number/7QBJS6RMOHJY3R2JPRY4WYH4JS/graph.json","events_json":"https://pith.science/api/pith-number/7QBJS6RMOHJY3R2JPRY4WYH4JS/events.json","paper":"https://pith.science/paper/7QBJS6RM"},"agent_actions":{"view_html":"https://pith.science/pith/7QBJS6RMOHJY3R2JPRY4WYH4JS","download_json":"https://pith.science/pith/7QBJS6RMOHJY3R2JPRY4WYH4JS.json","view_paper":"https://pith.science/paper/7QBJS6RM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.04879&json=true","fetch_graph":"https://pith.science/api/pith-number/7QBJS6RMOHJY3R2JPRY4WYH4JS/graph.json","fetch_events":"https://pith.science/api/pith-number/7QBJS6RMOHJY3R2JPRY4WYH4JS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QBJS6RMOHJY3R2JPRY4WYH4JS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QBJS6RMOHJY3R2JPRY4WYH4JS/action/storage_attestation","attest_author":"https://pith.science/pith/7QBJS6RMOHJY3R2JPRY4WYH4JS/action/author_attestation","sign_citation":"https://pith.science/pith/7QBJS6RMOHJY3R2JPRY4WYH4JS/action/citation_signature","submit_replication":"https://pith.science/pith/7QBJS6RMOHJY3R2JPRY4WYH4JS/action/replication_record"}},"created_at":"2026-07-05T04:13:15.119325+00:00","updated_at":"2026-07-05T04:13:15.119325+00:00"}