{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VRA3IWA7HSNEHK2XPYYI5XPMGC","short_pith_number":"pith:VRA3IWA7","schema_version":"1.0","canonical_sha256":"ac41b4581f3c9a43ab577e308eddec3084a0ef7c31dd0d6c54300db0586651dd","source":{"kind":"arxiv","id":"2407.05705","version":1},"attestation_state":"computed","paper":{"title":"Fast and Continual Knowledge Graph Embedding via Incremental LoRA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guozheng Li, Jiahao Wang, Jiajun Liu, Jinhua Gao, Ke Ji, Peng Wang, Wenjun Ke, Yining Li, Zijie Xu, Ziyu Shang","submitted_at":"2024-07-08T08:07:13Z","abstract_excerpt":"Continual Knowledge Graph Embedding (CKGE) aims to efficiently learn new knowledge and simultaneously preserve old knowledge. Dominant approaches primarily focus on alleviating catastrophic forgetting of old knowledge but neglect efficient learning for the emergence of new knowledge. However, in real-world scenarios, knowledge graphs (KGs) are continuously growing, which brings a significant challenge to fine-tuning KGE models efficiently. To address this issue, we propose a fast CKGE framework (\\model), incorporating an incremental low-rank adapter (\\mec) mechanism to efficiently acquire new "},"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":"2407.05705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-08T08:07:13Z","cross_cats_sorted":[],"title_canon_sha256":"cb39f43b23367615edc77b5f709188e804f21b7b3285fe20896f63a686fb0b0c","abstract_canon_sha256":"98a3a55b8c73edbd620d11032ad9a8c5b11f986c17e9bb1a577dbedfb99c7d37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:17.659188Z","signature_b64":"VUNY2dswSPs4U0qVRsWmq7UF1IctrwFtALKaGG3Bicn/Z7UOycjsMAMTCLbObYM0xMm+S6h/K7BT08dvygyACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac41b4581f3c9a43ab577e308eddec3084a0ef7c31dd0d6c54300db0586651dd","last_reissued_at":"2026-07-05T08:41:17.658677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:17.658677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Continual Knowledge Graph Embedding via Incremental LoRA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guozheng Li, Jiahao Wang, Jiajun Liu, Jinhua Gao, Ke Ji, Peng Wang, Wenjun Ke, Yining Li, Zijie Xu, Ziyu Shang","submitted_at":"2024-07-08T08:07:13Z","abstract_excerpt":"Continual Knowledge Graph Embedding (CKGE) aims to efficiently learn new knowledge and simultaneously preserve old knowledge. Dominant approaches primarily focus on alleviating catastrophic forgetting of old knowledge but neglect efficient learning for the emergence of new knowledge. However, in real-world scenarios, knowledge graphs (KGs) are continuously growing, which brings a significant challenge to fine-tuning KGE models efficiently. To address this issue, we propose a fast CKGE framework (\\model), incorporating an incremental low-rank adapter (\\mec) mechanism to efficiently acquire new "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05705","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/2407.05705/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":"2407.05705","created_at":"2026-07-05T08:41:17.658756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05705v1","created_at":"2026-07-05T08:41:17.658756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05705","created_at":"2026-07-05T08:41:17.658756+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRA3IWA7HSNE","created_at":"2026-07-05T08:41:17.658756+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRA3IWA7HSNEHK2X","created_at":"2026-07-05T08:41:17.658756+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRA3IWA7","created_at":"2026-07-05T08:41:17.658756+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02778","citing_title":"When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10947","citing_title":"Multi-Faceted Continual Knowledge Graph Embedding for Semantic-Aware Link Prediction","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRA3IWA7HSNEHK2XPYYI5XPMGC","json":"https://pith.science/pith/VRA3IWA7HSNEHK2XPYYI5XPMGC.json","graph_json":"https://pith.science/api/pith-number/VRA3IWA7HSNEHK2XPYYI5XPMGC/graph.json","events_json":"https://pith.science/api/pith-number/VRA3IWA7HSNEHK2XPYYI5XPMGC/events.json","paper":"https://pith.science/paper/VRA3IWA7"},"agent_actions":{"view_html":"https://pith.science/pith/VRA3IWA7HSNEHK2XPYYI5XPMGC","download_json":"https://pith.science/pith/VRA3IWA7HSNEHK2XPYYI5XPMGC.json","view_paper":"https://pith.science/paper/VRA3IWA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05705&json=true","fetch_graph":"https://pith.science/api/pith-number/VRA3IWA7HSNEHK2XPYYI5XPMGC/graph.json","fetch_events":"https://pith.science/api/pith-number/VRA3IWA7HSNEHK2XPYYI5XPMGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRA3IWA7HSNEHK2XPYYI5XPMGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRA3IWA7HSNEHK2XPYYI5XPMGC/action/storage_attestation","attest_author":"https://pith.science/pith/VRA3IWA7HSNEHK2XPYYI5XPMGC/action/author_attestation","sign_citation":"https://pith.science/pith/VRA3IWA7HSNEHK2XPYYI5XPMGC/action/citation_signature","submit_replication":"https://pith.science/pith/VRA3IWA7HSNEHK2XPYYI5XPMGC/action/replication_record"}},"created_at":"2026-07-05T08:41:17.658756+00:00","updated_at":"2026-07-05T08:41:17.658756+00:00"}