{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UO5NXMJNNBCWBMMNASRHCQH46I","short_pith_number":"pith:UO5NXMJN","schema_version":"1.0","canonical_sha256":"a3badbb12d684560b18d04a27140fcf22d41e7a9a66aba3ee7212bd392c60657","source":{"kind":"arxiv","id":"1911.06136","version":3},"attestation_state":"computed","paper":{"title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jian Tang, Juanzi Li, Tianyu Gao, Xiaozhi Wang, Zhaocheng Zhu, Zhengyan Zhang, Zhiyuan Liu","submitted_at":"2019-11-13T05:21:45Z","abstract_excerpt":"Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. In contrast, knowledge embedding (KE) methods can effectively represent the relational facts in knowledge graphs (KGs) with informative entity embeddings, but conventional KE models cannot take full advantage of the abundant textual information. In this paper, we propose a unified model for Knowledge Embedding and Pre-trained LanguagE Representation (KEPLER), which can not only better integrate factual knowledge into PLMs but also produce effective text-enhanced KE with the strong PLMs. In KEPLER"},"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":"1911.06136","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-13T05:21:45Z","cross_cats_sorted":[],"title_canon_sha256":"c05f367d7c121c3b931f42f382623ae7d6b0520d03d55c8ece66e000c1165c93","abstract_canon_sha256":"60be55eab3ff37707703aada9861bcbfead9bf04ed01e3238035e2d270143d38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:36.420912Z","signature_b64":"XN9/mILDXOKWJlTqcuf1CCuGEozmcCwGtVnmrcBZxcSU2wMnzgsXtiMn3Bm6J7hQqr1SGMu7bZdDkt0LfjmYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3badbb12d684560b18d04a27140fcf22d41e7a9a66aba3ee7212bd392c60657","last_reissued_at":"2026-07-05T01:53:36.420422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:36.420422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jian Tang, Juanzi Li, Tianyu Gao, Xiaozhi Wang, Zhaocheng Zhu, Zhengyan Zhang, Zhiyuan Liu","submitted_at":"2019-11-13T05:21:45Z","abstract_excerpt":"Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. In contrast, knowledge embedding (KE) methods can effectively represent the relational facts in knowledge graphs (KGs) with informative entity embeddings, but conventional KE models cannot take full advantage of the abundant textual information. In this paper, we propose a unified model for Knowledge Embedding and Pre-trained LanguagE Representation (KEPLER), which can not only better integrate factual knowledge into PLMs but also produce effective text-enhanced KE with the strong PLMs. In KEPLER"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06136","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/1911.06136/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":"1911.06136","created_at":"2026-07-05T01:53:36.420483+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06136v3","created_at":"2026-07-05T01:53:36.420483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06136","created_at":"2026-07-05T01:53:36.420483+00:00"},{"alias_kind":"pith_short_12","alias_value":"UO5NXMJNNBCW","created_at":"2026-07-05T01:53:36.420483+00:00"},{"alias_kind":"pith_short_16","alias_value":"UO5NXMJNNBCWBMMN","created_at":"2026-07-05T01:53:36.420483+00:00"},{"alias_kind":"pith_short_8","alias_value":"UO5NXMJN","created_at":"2026-07-05T01:53:36.420483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2010.03496","citing_title":"Inductive Entity Representations from Text via Link Prediction","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UO5NXMJNNBCWBMMNASRHCQH46I","json":"https://pith.science/pith/UO5NXMJNNBCWBMMNASRHCQH46I.json","graph_json":"https://pith.science/api/pith-number/UO5NXMJNNBCWBMMNASRHCQH46I/graph.json","events_json":"https://pith.science/api/pith-number/UO5NXMJNNBCWBMMNASRHCQH46I/events.json","paper":"https://pith.science/paper/UO5NXMJN"},"agent_actions":{"view_html":"https://pith.science/pith/UO5NXMJNNBCWBMMNASRHCQH46I","download_json":"https://pith.science/pith/UO5NXMJNNBCWBMMNASRHCQH46I.json","view_paper":"https://pith.science/paper/UO5NXMJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06136&json=true","fetch_graph":"https://pith.science/api/pith-number/UO5NXMJNNBCWBMMNASRHCQH46I/graph.json","fetch_events":"https://pith.science/api/pith-number/UO5NXMJNNBCWBMMNASRHCQH46I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UO5NXMJNNBCWBMMNASRHCQH46I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UO5NXMJNNBCWBMMNASRHCQH46I/action/storage_attestation","attest_author":"https://pith.science/pith/UO5NXMJNNBCWBMMNASRHCQH46I/action/author_attestation","sign_citation":"https://pith.science/pith/UO5NXMJNNBCWBMMNASRHCQH46I/action/citation_signature","submit_replication":"https://pith.science/pith/UO5NXMJNNBCWBMMNASRHCQH46I/action/replication_record"}},"created_at":"2026-07-05T01:53:36.420483+00:00","updated_at":"2026-07-05T01:53:36.420483+00:00"}