{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QZUMTZNZW4V5DPLPXIYW4MMUON","short_pith_number":"pith:QZUMTZNZ","schema_version":"1.0","canonical_sha256":"8668c9e5b9b72bd1bd6fba316e3194735d9a60c3ea905cf853c77c2684b1edcb","source":{"kind":"arxiv","id":"1909.07606","version":1},"attestation_state":"computed","paper":{"title":"K-BERT: Enabling Language Representation with Knowledge Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Haotang Deng, Peng Zhou, Ping Wang, Qi Ju, Weijie Liu, Zhe Zhao, Zhiruo Wang","submitted_at":"2019-09-17T06:16:04Z","abstract_excerpt":"Pre-trained language representation models, such as BERT, capture a general language representation from large-scale corpora, but lack domain-specific knowledge. When reading a domain text, experts make inferences with relevant knowledge. For machines to achieve this capability, we propose a knowledge-enabled language representation model (K-BERT) with knowledge graphs (KGs), in which triples are injected into the sentences as domain knowledge. However, too much knowledge incorporation may divert the sentence from its correct meaning, which is called knowledge noise (KN) issue. To overcome KN,"},"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":"1909.07606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-17T06:16:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b1817c72d56ebe10dadb517e96388544fcaa552b3f36aa630ebb994a6abb26f6","abstract_canon_sha256":"8be9f725af0c0f31f6f8abac26cb4c3e8e59a5118d6629affd686fe95ca51e83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:15.882808Z","signature_b64":"K/uwgxikeOE52APHCzBlicqCfGIaYpzQ1SBtIQf3jMhzDk6wNHIndQEmBqynWOaUed0r9uLw+CpR3N/zuGyzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8668c9e5b9b72bd1bd6fba316e3194735d9a60c3ea905cf853c77c2684b1edcb","last_reissued_at":"2026-07-05T00:05:15.882422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:15.882422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"K-BERT: Enabling Language Representation with Knowledge Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Haotang Deng, Peng Zhou, Ping Wang, Qi Ju, Weijie Liu, Zhe Zhao, Zhiruo Wang","submitted_at":"2019-09-17T06:16:04Z","abstract_excerpt":"Pre-trained language representation models, such as BERT, capture a general language representation from large-scale corpora, but lack domain-specific knowledge. When reading a domain text, experts make inferences with relevant knowledge. For machines to achieve this capability, we propose a knowledge-enabled language representation model (K-BERT) with knowledge graphs (KGs), in which triples are injected into the sentences as domain knowledge. However, too much knowledge incorporation may divert the sentence from its correct meaning, which is called knowledge noise (KN) issue. To overcome KN,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07606","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/1909.07606/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":"1909.07606","created_at":"2026-07-05T00:05:15.882480+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.07606v1","created_at":"2026-07-05T00:05:15.882480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07606","created_at":"2026-07-05T00:05:15.882480+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZUMTZNZW4V5","created_at":"2026-07-05T00:05:15.882480+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZUMTZNZW4V5DPLP","created_at":"2026-07-05T00:05:15.882480+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZUMTZNZ","created_at":"2026-07-05T00:05:15.882480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20170","citing_title":"KoRe: Compact Knowledge Representations for Large Language Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZUMTZNZW4V5DPLPXIYW4MMUON","json":"https://pith.science/pith/QZUMTZNZW4V5DPLPXIYW4MMUON.json","graph_json":"https://pith.science/api/pith-number/QZUMTZNZW4V5DPLPXIYW4MMUON/graph.json","events_json":"https://pith.science/api/pith-number/QZUMTZNZW4V5DPLPXIYW4MMUON/events.json","paper":"https://pith.science/paper/QZUMTZNZ"},"agent_actions":{"view_html":"https://pith.science/pith/QZUMTZNZW4V5DPLPXIYW4MMUON","download_json":"https://pith.science/pith/QZUMTZNZW4V5DPLPXIYW4MMUON.json","view_paper":"https://pith.science/paper/QZUMTZNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.07606&json=true","fetch_graph":"https://pith.science/api/pith-number/QZUMTZNZW4V5DPLPXIYW4MMUON/graph.json","fetch_events":"https://pith.science/api/pith-number/QZUMTZNZW4V5DPLPXIYW4MMUON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZUMTZNZW4V5DPLPXIYW4MMUON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZUMTZNZW4V5DPLPXIYW4MMUON/action/storage_attestation","attest_author":"https://pith.science/pith/QZUMTZNZW4V5DPLPXIYW4MMUON/action/author_attestation","sign_citation":"https://pith.science/pith/QZUMTZNZW4V5DPLPXIYW4MMUON/action/citation_signature","submit_replication":"https://pith.science/pith/QZUMTZNZW4V5DPLPXIYW4MMUON/action/replication_record"}},"created_at":"2026-07-05T00:05:15.882480+00:00","updated_at":"2026-07-05T00:05:15.882480+00:00"}