{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BRJVJFR7WWTBY2FJU2FYGGVRSB","short_pith_number":"pith:BRJVJFR7","schema_version":"1.0","canonical_sha256":"0c5354963fb5a61c68a9a68b831ab1906c23ceda297aa2c43e55971732b4e6d5","source":{"kind":"arxiv","id":"1912.00552","version":2},"attestation_state":"computed","paper":{"title":"Sparse Graph Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shihao Ji, Yang Ye","submitted_at":"2019-12-02T02:25:01Z","abstract_excerpt":"Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks, such as node classification, link prediction and graph classification. Among the variants of GNNs, Graph Attention Networks (GATs) learn to assign dense attention coefficients over all neighbors of a node for feature aggregation, and improve the performance of many graph learning tasks. However, real-world graphs are often very large and noisy, and GATs are prone to overfitting if not regulari"},"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":"1912.00552","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T02:25:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bd3d95265ce9a005ff57aa5bc71e6834c22c394ac8eec432dd05c9c8fef3cd98","abstract_canon_sha256":"98a4baaf11240f58df6cbfb57d4c4a3cf6ed0906c1ac91c541a33f1d2fc56b56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:55.865334Z","signature_b64":"f4EXLx1IKZV2QHIg8Qz7g+tCEzaUpiCvBUKz1wJxMpzwLmTlgYMzZmntJhyTmMDP8ZZIr5oyu4R7KfT3Hm+uAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c5354963fb5a61c68a9a68b831ab1906c23ceda297aa2c43e55971732b4e6d5","last_reissued_at":"2026-07-05T02:30:55.864830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:55.864830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Graph Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shihao Ji, Yang Ye","submitted_at":"2019-12-02T02:25:01Z","abstract_excerpt":"Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks, such as node classification, link prediction and graph classification. Among the variants of GNNs, Graph Attention Networks (GATs) learn to assign dense attention coefficients over all neighbors of a node for feature aggregation, and improve the performance of many graph learning tasks. However, real-world graphs are often very large and noisy, and GATs are prone to overfitting if not regulari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00552","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/1912.00552/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":"1912.00552","created_at":"2026-07-05T02:30:55.864888+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00552v2","created_at":"2026-07-05T02:30:55.864888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00552","created_at":"2026-07-05T02:30:55.864888+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRJVJFR7WWTB","created_at":"2026-07-05T02:30:55.864888+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRJVJFR7WWTBY2FJ","created_at":"2026-07-05T02:30:55.864888+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRJVJFR7","created_at":"2026-07-05T02:30:55.864888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01223","citing_title":"Perspectives on Tsallis Statistics for Artificial Intelligence","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRJVJFR7WWTBY2FJU2FYGGVRSB","json":"https://pith.science/pith/BRJVJFR7WWTBY2FJU2FYGGVRSB.json","graph_json":"https://pith.science/api/pith-number/BRJVJFR7WWTBY2FJU2FYGGVRSB/graph.json","events_json":"https://pith.science/api/pith-number/BRJVJFR7WWTBY2FJU2FYGGVRSB/events.json","paper":"https://pith.science/paper/BRJVJFR7"},"agent_actions":{"view_html":"https://pith.science/pith/BRJVJFR7WWTBY2FJU2FYGGVRSB","download_json":"https://pith.science/pith/BRJVJFR7WWTBY2FJU2FYGGVRSB.json","view_paper":"https://pith.science/paper/BRJVJFR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00552&json=true","fetch_graph":"https://pith.science/api/pith-number/BRJVJFR7WWTBY2FJU2FYGGVRSB/graph.json","fetch_events":"https://pith.science/api/pith-number/BRJVJFR7WWTBY2FJU2FYGGVRSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRJVJFR7WWTBY2FJU2FYGGVRSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRJVJFR7WWTBY2FJU2FYGGVRSB/action/storage_attestation","attest_author":"https://pith.science/pith/BRJVJFR7WWTBY2FJU2FYGGVRSB/action/author_attestation","sign_citation":"https://pith.science/pith/BRJVJFR7WWTBY2FJU2FYGGVRSB/action/citation_signature","submit_replication":"https://pith.science/pith/BRJVJFR7WWTBY2FJU2FYGGVRSB/action/replication_record"}},"created_at":"2026-07-05T02:30:55.864888+00:00","updated_at":"2026-07-05T02:30:55.864888+00:00"}