{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L4LM5T2ZHPTA3TXQJJDYLB2WSS","short_pith_number":"pith:L4LM5T2Z","schema_version":"1.0","canonical_sha256":"5f16cecf593be60dcef04a47858756948fd65a66ef918f3f6b99fb61cd41794f","source":{"kind":"arxiv","id":"2605.18211","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Evgeny Kharlamov, Jingcheng Wu, Luu Huu Phuc, Mojtaba Nayyeri, Ratan Bahadur Thapa, Steffen Staab","submitted_at":"2026-05-18T10:56:14Z","abstract_excerpt":"We introduce Graph-Augmented Sequence-to-Sequence (GA-S2S), a novel framework that integrates a T5-small encoder-decoder with a Relational Graph Attention Network (RGAT) to improve link prediction in knowledge graphs. While existing Seq2Seq models rely solely on surface-level textual descriptions of entities and relations and at best, flatten the neighborhoods of a query entity into a single linear sequence, thereby discarding the inherent graph structure, GA-S2S jointly encodes both textual features and the full $k$-hop subgraph topology surrounding the query entity. By integrating raw encode"},"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":"2605.18211","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T10:56:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6396e8ecdbc99e21949b1f4f1a80e0356afa928e8db6eef327c564472158a3c2","abstract_canon_sha256":"4aabba649e959fbbf8b918721e42ee5989bda6f344b335fecd69d6952e6c1a02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:50.724952Z","signature_b64":"WQsgs/SchEx3w+guwskv5RDwU0DLvyL4L/tp5JL7NbXH5tZzVmTK4k6vda1wMEiclFQAFZom3I3YkbjcMLSkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f16cecf593be60dcef04a47858756948fd65a66ef918f3f6b99fb61cd41794f","last_reissued_at":"2026-05-20T00:05:50.724350Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:50.724350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Evgeny Kharlamov, Jingcheng Wu, Luu Huu Phuc, Mojtaba Nayyeri, Ratan Bahadur Thapa, Steffen Staab","submitted_at":"2026-05-18T10:56:14Z","abstract_excerpt":"We introduce Graph-Augmented Sequence-to-Sequence (GA-S2S), a novel framework that integrates a T5-small encoder-decoder with a Relational Graph Attention Network (RGAT) to improve link prediction in knowledge graphs. While existing Seq2Seq models rely solely on surface-level textual descriptions of entities and relations and at best, flatten the neighborhoods of a query entity into a single linear sequence, thereby discarding the inherent graph structure, GA-S2S jointly encodes both textual features and the full $k$-hop subgraph topology surrounding the query entity. By integrating raw encode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18211","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/2605.18211/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:58.973873Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.311124Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8d3314457fb7de09a3679e87daad285d7dc8104868ce6ac1f47569eece37909f"},"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":"2605.18211","created_at":"2026-05-20T00:05:50.724434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18211v1","created_at":"2026-05-20T00:05:50.724434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18211","created_at":"2026-05-20T00:05:50.724434+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4LM5T2ZHPTA","created_at":"2026-05-20T00:05:50.724434+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4LM5T2ZHPTA3TXQ","created_at":"2026-05-20T00:05:50.724434+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4LM5T2Z","created_at":"2026-05-20T00:05:50.724434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4LM5T2ZHPTA3TXQJJDYLB2WSS","json":"https://pith.science/pith/L4LM5T2ZHPTA3TXQJJDYLB2WSS.json","graph_json":"https://pith.science/api/pith-number/L4LM5T2ZHPTA3TXQJJDYLB2WSS/graph.json","events_json":"https://pith.science/api/pith-number/L4LM5T2ZHPTA3TXQJJDYLB2WSS/events.json","paper":"https://pith.science/paper/L4LM5T2Z"},"agent_actions":{"view_html":"https://pith.science/pith/L4LM5T2ZHPTA3TXQJJDYLB2WSS","download_json":"https://pith.science/pith/L4LM5T2ZHPTA3TXQJJDYLB2WSS.json","view_paper":"https://pith.science/paper/L4LM5T2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18211&json=true","fetch_graph":"https://pith.science/api/pith-number/L4LM5T2ZHPTA3TXQJJDYLB2WSS/graph.json","fetch_events":"https://pith.science/api/pith-number/L4LM5T2ZHPTA3TXQJJDYLB2WSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4LM5T2ZHPTA3TXQJJDYLB2WSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4LM5T2ZHPTA3TXQJJDYLB2WSS/action/storage_attestation","attest_author":"https://pith.science/pith/L4LM5T2ZHPTA3TXQJJDYLB2WSS/action/author_attestation","sign_citation":"https://pith.science/pith/L4LM5T2ZHPTA3TXQJJDYLB2WSS/action/citation_signature","submit_replication":"https://pith.science/pith/L4LM5T2ZHPTA3TXQJJDYLB2WSS/action/replication_record"}},"created_at":"2026-05-20T00:05:50.724434+00:00","updated_at":"2026-05-20T00:05:50.724434+00:00"}