{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WQ7D4LNJ6UCGVK63EHTAEFVLM4","short_pith_number":"pith:WQ7D4LNJ","schema_version":"1.0","canonical_sha256":"b43e3e2da9f5046aabdb21e60216ab673d8d3dd70980c2014e1a213a58cc2595","source":{"kind":"arxiv","id":"1909.11855","version":13},"attestation_state":"computed","paper":{"title":"Universal Graph Transformer Self-Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dai Quoc Nguyen, Dinh Phung, Tu Dinh Nguyen","submitted_at":"2019-09-26T02:39:59Z","abstract_excerpt":"We introduce a transformer-based GNN model, named UGformer, to learn graph representations. In particular, we present two UGformer variants, wherein the first variant (publicized in September 2019) is to leverage the transformer on a set of sampled neighbors for each input node, while the second (publicized in May 2021) is to leverage the transformer on all input nodes. Experimental results demonstrate that the first UGformer variant achieves state-of-the-art accuracies on benchmark datasets for graph classification in both inductive setting and unsupervised transductive setting; and the secon"},"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":"1909.11855","kind":"arxiv","version":13},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T02:39:59Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"585f65532c97d4188e1afe52f7bb71ad0060d1e06b215da644df238425621368","abstract_canon_sha256":"5ba3cd9aa1a80c974ab04a92af3ea9b430a7a2feada02bcaada1a72a0c8cab02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:50.792191Z","signature_b64":"solhihQE7WoStJeARtXNCUvkLZv6Mb/8d15hvVydRzHdmAysucwLssNgDDGdcA5zFnmrVCegBukK7cH3vEIhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b43e3e2da9f5046aabdb21e60216ab673d8d3dd70980c2014e1a213a58cc2595","last_reissued_at":"2026-07-05T04:02:50.791605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:50.791605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Graph Transformer Self-Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dai Quoc Nguyen, Dinh Phung, Tu Dinh Nguyen","submitted_at":"2019-09-26T02:39:59Z","abstract_excerpt":"We introduce a transformer-based GNN model, named UGformer, to learn graph representations. In particular, we present two UGformer variants, wherein the first variant (publicized in September 2019) is to leverage the transformer on a set of sampled neighbors for each input node, while the second (publicized in May 2021) is to leverage the transformer on all input nodes. Experimental results demonstrate that the first UGformer variant achieves state-of-the-art accuracies on benchmark datasets for graph classification in both inductive setting and unsupervised transductive setting; and the secon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11855","kind":"arxiv","version":13},"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/1909.11855/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":"1909.11855","created_at":"2026-07-05T04:02:50.791861+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11855v13","created_at":"2026-07-05T04:02:50.791861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11855","created_at":"2026-07-05T04:02:50.791861+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ7D4LNJ6UCG","created_at":"2026-07-05T04:02:50.791861+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ7D4LNJ6UCGVK63","created_at":"2026-07-05T04:02:50.791861+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ7D4LNJ","created_at":"2026-07-05T04:02:50.791861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22429","citing_title":"Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation","ref_index":276,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08679","citing_title":"Attention-based graph neural networks: a survey","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQ7D4LNJ6UCGVK63EHTAEFVLM4","json":"https://pith.science/pith/WQ7D4LNJ6UCGVK63EHTAEFVLM4.json","graph_json":"https://pith.science/api/pith-number/WQ7D4LNJ6UCGVK63EHTAEFVLM4/graph.json","events_json":"https://pith.science/api/pith-number/WQ7D4LNJ6UCGVK63EHTAEFVLM4/events.json","paper":"https://pith.science/paper/WQ7D4LNJ"},"agent_actions":{"view_html":"https://pith.science/pith/WQ7D4LNJ6UCGVK63EHTAEFVLM4","download_json":"https://pith.science/pith/WQ7D4LNJ6UCGVK63EHTAEFVLM4.json","view_paper":"https://pith.science/paper/WQ7D4LNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11855&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ7D4LNJ6UCGVK63EHTAEFVLM4/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ7D4LNJ6UCGVK63EHTAEFVLM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ7D4LNJ6UCGVK63EHTAEFVLM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ7D4LNJ6UCGVK63EHTAEFVLM4/action/storage_attestation","attest_author":"https://pith.science/pith/WQ7D4LNJ6UCGVK63EHTAEFVLM4/action/author_attestation","sign_citation":"https://pith.science/pith/WQ7D4LNJ6UCGVK63EHTAEFVLM4/action/citation_signature","submit_replication":"https://pith.science/pith/WQ7D4LNJ6UCGVK63EHTAEFVLM4/action/replication_record"}},"created_at":"2026-07-05T04:02:50.791861+00:00","updated_at":"2026-07-05T04:02:50.791861+00:00"}