{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZSN35PK2JRAUGH4URLFR24OK3B","short_pith_number":"pith:ZSN35PK2","schema_version":"1.0","canonical_sha256":"cc9bbebd5a4c41431f948acb1d71cad845a42dd0dda3ea198c4be14893a7fbbc","source":{"kind":"arxiv","id":"2403.01972","version":1},"attestation_state":"computed","paper":{"title":"Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derong Xu, Enhong Chen, Tong Xu, Xiangyu Zhao, Xian Wu, Yefeng Zheng, Zhenxi Lin, Zhihong Zhu, Ziheng Zhang","submitted_at":"2024-03-04T12:16:15Z","abstract_excerpt":"Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs) by making predictions for missing links. Description-based KGC leverages pre-trained language models to learn entity and relation representations with their names or descriptions, which shows promising results. However, the performance of description-based KGC is still limited by the quality of text and the incomplete structure, as it lacks sufficient entity descriptions and relies solely on relation names, leading to sub-optimal results. To address this issue, we propose MPIKGC, a gener"},"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":"2403.01972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T12:16:15Z","cross_cats_sorted":[],"title_canon_sha256":"b380ce99757bf6e053d6353b70aa344e4f37a273473acc92cb5a081500822da7","abstract_canon_sha256":"1f250e105fe2ea86897f925e29c60098048f6f8fd90fb8c5a7ad1ded6c05fc59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:54.888104Z","signature_b64":"FjpDnJLRmioc5fCDPM+3DkwRavkO1oGrq2KXlLdWH9DgU8nFVu9vfL2GbZZ108kr0jGPVCEgv8iPYOsuz00kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc9bbebd5a4c41431f948acb1d71cad845a42dd0dda3ea198c4be14893a7fbbc","last_reissued_at":"2026-07-05T07:51:54.887595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:54.887595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derong Xu, Enhong Chen, Tong Xu, Xiangyu Zhao, Xian Wu, Yefeng Zheng, Zhenxi Lin, Zhihong Zhu, Ziheng Zhang","submitted_at":"2024-03-04T12:16:15Z","abstract_excerpt":"Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs) by making predictions for missing links. Description-based KGC leverages pre-trained language models to learn entity and relation representations with their names or descriptions, which shows promising results. However, the performance of description-based KGC is still limited by the quality of text and the incomplete structure, as it lacks sufficient entity descriptions and relies solely on relation names, leading to sub-optimal results. To address this issue, we propose MPIKGC, a gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01972","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/2403.01972/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":"2403.01972","created_at":"2026-07-05T07:51:54.887659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01972v1","created_at":"2026-07-05T07:51:54.887659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01972","created_at":"2026-07-05T07:51:54.887659+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSN35PK2JRAU","created_at":"2026-07-05T07:51:54.887659+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSN35PK2JRAUGH4U","created_at":"2026-07-05T07:51:54.887659+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSN35PK2","created_at":"2026-07-05T07:51:54.887659+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01166","citing_title":"Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSN35PK2JRAUGH4URLFR24OK3B","json":"https://pith.science/pith/ZSN35PK2JRAUGH4URLFR24OK3B.json","graph_json":"https://pith.science/api/pith-number/ZSN35PK2JRAUGH4URLFR24OK3B/graph.json","events_json":"https://pith.science/api/pith-number/ZSN35PK2JRAUGH4URLFR24OK3B/events.json","paper":"https://pith.science/paper/ZSN35PK2"},"agent_actions":{"view_html":"https://pith.science/pith/ZSN35PK2JRAUGH4URLFR24OK3B","download_json":"https://pith.science/pith/ZSN35PK2JRAUGH4URLFR24OK3B.json","view_paper":"https://pith.science/paper/ZSN35PK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01972&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSN35PK2JRAUGH4URLFR24OK3B/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSN35PK2JRAUGH4URLFR24OK3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSN35PK2JRAUGH4URLFR24OK3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSN35PK2JRAUGH4URLFR24OK3B/action/storage_attestation","attest_author":"https://pith.science/pith/ZSN35PK2JRAUGH4URLFR24OK3B/action/author_attestation","sign_citation":"https://pith.science/pith/ZSN35PK2JRAUGH4URLFR24OK3B/action/citation_signature","submit_replication":"https://pith.science/pith/ZSN35PK2JRAUGH4URLFR24OK3B/action/replication_record"}},"created_at":"2026-07-05T07:51:54.887659+00:00","updated_at":"2026-07-05T07:51:54.887659+00:00"}