{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VYCZHYLB4G6RMVAXZOPJ33ZFCR","short_pith_number":"pith:VYCZHYLB","schema_version":"1.0","canonical_sha256":"ae0593e161e1bd165417cb9e9def251463a34ad96c97da6af89dd0afc8fcf66b","source":{"kind":"arxiv","id":"2304.11533","version":1},"attestation_state":"computed","paper":{"title":"Bi-Level Attention Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Roshni G. Iyer, Wei Wang, Yizhou Sun","submitted_at":"2023-04-23T04:18:56Z","abstract_excerpt":"Recent graph neural networks (GNNs) with the attention mechanism have historically been limited to small-scale homogeneous graphs (HoGs). However, GNNs handling heterogeneous graphs (HeGs), which contain several entity and relation types, all have shortcomings in handling attention. Most GNNs that learn graph attention for HeGs learn either node-level or relation-level attention, but not both, limiting their ability to predict both important entities and relations in the HeG. Even the best existing method that learns both levels of attention has the limitation of assuming graph relations are i"},"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":"2304.11533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-23T04:18:56Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"687e6b63376f99135c304e543024c37a8025587e765d7849c290fb00225ce461","abstract_canon_sha256":"f13770de1de81b8a94e5bfef4f0ee2fabf2eb7b65c77d6348a7ace7f7491016b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:33.989001Z","signature_b64":"C7gEqpptyl9aakRj5PmfuMjRyGQ7dKGs38Ru1TenPKpN1Cs8N78KNEuyISAlqQcJB1W/jYihrtGPAHkjoBudBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae0593e161e1bd165417cb9e9def251463a34ad96c97da6af89dd0afc8fcf66b","last_reissued_at":"2026-07-05T06:03:33.988610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:33.988610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bi-Level Attention Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Roshni G. Iyer, Wei Wang, Yizhou Sun","submitted_at":"2023-04-23T04:18:56Z","abstract_excerpt":"Recent graph neural networks (GNNs) with the attention mechanism have historically been limited to small-scale homogeneous graphs (HoGs). However, GNNs handling heterogeneous graphs (HeGs), which contain several entity and relation types, all have shortcomings in handling attention. Most GNNs that learn graph attention for HeGs learn either node-level or relation-level attention, but not both, limiting their ability to predict both important entities and relations in the HeG. Even the best existing method that learns both levels of attention has the limitation of assuming graph relations are i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11533","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/2304.11533/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":"2304.11533","created_at":"2026-07-05T06:03:33.988673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11533v1","created_at":"2026-07-05T06:03:33.988673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11533","created_at":"2026-07-05T06:03:33.988673+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYCZHYLB4G6R","created_at":"2026-07-05T06:03:33.988673+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYCZHYLB4G6RMVAX","created_at":"2026-07-05T06:03:33.988673+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYCZHYLB","created_at":"2026-07-05T06:03:33.988673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14182","citing_title":"From Bias to Behavior: Learning Bull-Bear Market Dynamics with Contrastive Modeling","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYCZHYLB4G6RMVAXZOPJ33ZFCR","json":"https://pith.science/pith/VYCZHYLB4G6RMVAXZOPJ33ZFCR.json","graph_json":"https://pith.science/api/pith-number/VYCZHYLB4G6RMVAXZOPJ33ZFCR/graph.json","events_json":"https://pith.science/api/pith-number/VYCZHYLB4G6RMVAXZOPJ33ZFCR/events.json","paper":"https://pith.science/paper/VYCZHYLB"},"agent_actions":{"view_html":"https://pith.science/pith/VYCZHYLB4G6RMVAXZOPJ33ZFCR","download_json":"https://pith.science/pith/VYCZHYLB4G6RMVAXZOPJ33ZFCR.json","view_paper":"https://pith.science/paper/VYCZHYLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11533&json=true","fetch_graph":"https://pith.science/api/pith-number/VYCZHYLB4G6RMVAXZOPJ33ZFCR/graph.json","fetch_events":"https://pith.science/api/pith-number/VYCZHYLB4G6RMVAXZOPJ33ZFCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYCZHYLB4G6RMVAXZOPJ33ZFCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYCZHYLB4G6RMVAXZOPJ33ZFCR/action/storage_attestation","attest_author":"https://pith.science/pith/VYCZHYLB4G6RMVAXZOPJ33ZFCR/action/author_attestation","sign_citation":"https://pith.science/pith/VYCZHYLB4G6RMVAXZOPJ33ZFCR/action/citation_signature","submit_replication":"https://pith.science/pith/VYCZHYLB4G6RMVAXZOPJ33ZFCR/action/replication_record"}},"created_at":"2026-07-05T06:03:33.988673+00:00","updated_at":"2026-07-05T06:03:33.988673+00:00"}