{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SSVBE6OMS6C7HZ4VLCNQXTBWQZ","short_pith_number":"pith:SSVBE6OM","schema_version":"1.0","canonical_sha256":"94aa1279cc9785f3e795589b0bcc3686563a0b5c73ac13b9bb55e320e1757528","source":{"kind":"arxiv","id":"2402.01729","version":3},"attestation_state":"computed","paper":{"title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dawei Li, Huan Liu, Tianlong Chen, Zhen Tan","submitted_at":"2024-01-28T08:56:49Z","abstract_excerpt":"While textual information significantly enhances the performance of pre-trained language models (PLMs) in knowledge graph completion (KGC), the static and noisy nature of existing corpora collected from Wikipedia articles or synsets definitions often limits the potential of PLM-based KGC models. To surmount these challenges, we introduce the Contextualization Distillation strategy, a versatile plug-in-and-play approach compatible with both discriminative and generative KGC frameworks. Our method begins by instructing large language models (LLMs) to transform compact, structural triplets into c"},"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":"2402.01729","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-28T08:56:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"942955669a2e79da40b24fa0c4a16ed898de8e0808dcec805ce5ee0cdff8019e","abstract_canon_sha256":"2267e88f7779b97d26871d233f585165dde00c99a282232446be9e4b51bc38a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:52.446037Z","signature_b64":"4kPWvvZ8MDENxktx4WCWvGf37fp92TtytSH50zI/AP8mfStz+bkDQeirHAybnYuMATy1l+BpuqkppBTv9mBfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94aa1279cc9785f3e795589b0bcc3686563a0b5c73ac13b9bb55e320e1757528","last_reissued_at":"2026-07-05T07:48:52.445564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:52.445564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dawei Li, Huan Liu, Tianlong Chen, Zhen Tan","submitted_at":"2024-01-28T08:56:49Z","abstract_excerpt":"While textual information significantly enhances the performance of pre-trained language models (PLMs) in knowledge graph completion (KGC), the static and noisy nature of existing corpora collected from Wikipedia articles or synsets definitions often limits the potential of PLM-based KGC models. To surmount these challenges, we introduce the Contextualization Distillation strategy, a versatile plug-in-and-play approach compatible with both discriminative and generative KGC frameworks. Our method begins by instructing large language models (LLMs) to transform compact, structural triplets into c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01729","kind":"arxiv","version":3},"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/2402.01729/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":"2402.01729","created_at":"2026-07-05T07:48:52.445620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01729v3","created_at":"2026-07-05T07:48:52.445620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01729","created_at":"2026-07-05T07:48:52.445620+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSVBE6OMS6C7","created_at":"2026-07-05T07:48:52.445620+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSVBE6OMS6C7HZ4V","created_at":"2026-07-05T07:48:52.445620+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSVBE6OM","created_at":"2026-07-05T07:48:52.445620+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03576","citing_title":"KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Models","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSVBE6OMS6C7HZ4VLCNQXTBWQZ","json":"https://pith.science/pith/SSVBE6OMS6C7HZ4VLCNQXTBWQZ.json","graph_json":"https://pith.science/api/pith-number/SSVBE6OMS6C7HZ4VLCNQXTBWQZ/graph.json","events_json":"https://pith.science/api/pith-number/SSVBE6OMS6C7HZ4VLCNQXTBWQZ/events.json","paper":"https://pith.science/paper/SSVBE6OM"},"agent_actions":{"view_html":"https://pith.science/pith/SSVBE6OMS6C7HZ4VLCNQXTBWQZ","download_json":"https://pith.science/pith/SSVBE6OMS6C7HZ4VLCNQXTBWQZ.json","view_paper":"https://pith.science/paper/SSVBE6OM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01729&json=true","fetch_graph":"https://pith.science/api/pith-number/SSVBE6OMS6C7HZ4VLCNQXTBWQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SSVBE6OMS6C7HZ4VLCNQXTBWQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSVBE6OMS6C7HZ4VLCNQXTBWQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSVBE6OMS6C7HZ4VLCNQXTBWQZ/action/storage_attestation","attest_author":"https://pith.science/pith/SSVBE6OMS6C7HZ4VLCNQXTBWQZ/action/author_attestation","sign_citation":"https://pith.science/pith/SSVBE6OMS6C7HZ4VLCNQXTBWQZ/action/citation_signature","submit_replication":"https://pith.science/pith/SSVBE6OMS6C7HZ4VLCNQXTBWQZ/action/replication_record"}},"created_at":"2026-07-05T07:48:52.445620+00:00","updated_at":"2026-07-05T07:48:52.445620+00:00"}