{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YFJG6LV7MQBUGFOKSR5FE6GDBO","short_pith_number":"pith:YFJG6LV7","schema_version":"1.0","canonical_sha256":"c1526f2ebf64034315ca947a5278c30b86a62d405f449bb951537362d4f40deb","source":{"kind":"arxiv","id":"2109.05922","version":1},"attestation_state":"computed","paper":{"title":"r-GAT: Relational Graph Attention Network for Multi-Relational Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Meiqi Chen, Xiaoyu Kou, Yan Zhang, Yuan Zhang, Yuntao Li","submitted_at":"2021-09-13T12:43:00Z","abstract_excerpt":"Graph Attention Network (GAT) focuses on modelling simple undirected and single relational graph data only. This limits its ability to deal with more general and complex multi-relational graphs that contain entities with directed links of different labels (e.g., knowledge graphs). Therefore, directly applying GAT on multi-relational graphs leads to sub-optimal solutions. To tackle this issue, we propose r-GAT, a relational graph attention network to learn multi-channel entity representations. Specifically, each channel corresponds to a latent semantic aspect of an entity. This enables us to ag"},"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":"2109.05922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-13T12:43:00Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3c47d153e947b08f5debb687a94cef4f71368142c241ef43e3da1b1873da75d4","abstract_canon_sha256":"52c567b5bf6a7ebaaf00b6dfcaf7141a643208b13e207339f15a2bc9de73f810"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:43.759446Z","signature_b64":"SiekfFm4TIsUI8exqxawpnlC/7Ansxf0l/9naGoqeEJL0vnvEaxQ1o+xETS7R7R1B7kCKxg3sPQvLFW6vIAmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1526f2ebf64034315ca947a5278c30b86a62d405f449bb951537362d4f40deb","last_reissued_at":"2026-07-05T03:13:43.759000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:43.759000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"r-GAT: Relational Graph Attention Network for Multi-Relational Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Meiqi Chen, Xiaoyu Kou, Yan Zhang, Yuan Zhang, Yuntao Li","submitted_at":"2021-09-13T12:43:00Z","abstract_excerpt":"Graph Attention Network (GAT) focuses on modelling simple undirected and single relational graph data only. This limits its ability to deal with more general and complex multi-relational graphs that contain entities with directed links of different labels (e.g., knowledge graphs). Therefore, directly applying GAT on multi-relational graphs leads to sub-optimal solutions. To tackle this issue, we propose r-GAT, a relational graph attention network to learn multi-channel entity representations. Specifically, each channel corresponds to a latent semantic aspect of an entity. This enables us to ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05922","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/2109.05922/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":"2109.05922","created_at":"2026-07-05T03:13:43.759057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05922v1","created_at":"2026-07-05T03:13:43.759057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05922","created_at":"2026-07-05T03:13:43.759057+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFJG6LV7MQBU","created_at":"2026-07-05T03:13:43.759057+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFJG6LV7MQBUGFOK","created_at":"2026-07-05T03:13:43.759057+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFJG6LV7","created_at":"2026-07-05T03:13:43.759057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06915","citing_title":"Graph Neural Networks in Modern AI-aided Drug Discovery","ref_index":83,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFJG6LV7MQBUGFOKSR5FE6GDBO","json":"https://pith.science/pith/YFJG6LV7MQBUGFOKSR5FE6GDBO.json","graph_json":"https://pith.science/api/pith-number/YFJG6LV7MQBUGFOKSR5FE6GDBO/graph.json","events_json":"https://pith.science/api/pith-number/YFJG6LV7MQBUGFOKSR5FE6GDBO/events.json","paper":"https://pith.science/paper/YFJG6LV7"},"agent_actions":{"view_html":"https://pith.science/pith/YFJG6LV7MQBUGFOKSR5FE6GDBO","download_json":"https://pith.science/pith/YFJG6LV7MQBUGFOKSR5FE6GDBO.json","view_paper":"https://pith.science/paper/YFJG6LV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05922&json=true","fetch_graph":"https://pith.science/api/pith-number/YFJG6LV7MQBUGFOKSR5FE6GDBO/graph.json","fetch_events":"https://pith.science/api/pith-number/YFJG6LV7MQBUGFOKSR5FE6GDBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFJG6LV7MQBUGFOKSR5FE6GDBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFJG6LV7MQBUGFOKSR5FE6GDBO/action/storage_attestation","attest_author":"https://pith.science/pith/YFJG6LV7MQBUGFOKSR5FE6GDBO/action/author_attestation","sign_citation":"https://pith.science/pith/YFJG6LV7MQBUGFOKSR5FE6GDBO/action/citation_signature","submit_replication":"https://pith.science/pith/YFJG6LV7MQBUGFOKSR5FE6GDBO/action/replication_record"}},"created_at":"2026-07-05T03:13:43.759057+00:00","updated_at":"2026-07-05T03:13:43.759057+00:00"}