{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WV6QO74TKT6FKZQ6TONU2B3IED","short_pith_number":"pith:WV6QO74T","schema_version":"1.0","canonical_sha256":"b57d077f9354fc55661e9b9b4d076820cb18f2630dd6223ac4ff6810089e6aca","source":{"kind":"arxiv","id":"2203.02167","version":1},"attestation_state":"computed","paper":{"title":"SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingming Liu, Liang Wang, Wei Zhao, Zhuoyu Wei","submitted_at":"2022-03-04T07:36:30Z","abstract_excerpt":"Knowledge graph completion (KGC) aims to reason over known facts and infer the missing links. Text-based methods such as KGBERT (Yao et al., 2019) learn entity representations from natural language descriptions, and have the potential for inductive KGC. However, the performance of text-based methods still largely lag behind graph embedding-based methods like TransE (Bordes et al., 2013) and RotatE (Sun et al., 2019b). In this paper, we identify that the key issue is efficient contrastive learning. To improve the learning efficiency, we introduce three types of negatives: in-batch negatives, pr"},"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":"2203.02167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-04T07:36:30Z","cross_cats_sorted":[],"title_canon_sha256":"e15a6340302650a6a42288586fb59942cccbf43ea1e7cb98ba922f9c0497a05a","abstract_canon_sha256":"442b54bc82f4af45ac8401803124f103ae8d940972bd0d53b5c5b503f2a768ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:01.784237Z","signature_b64":"gn7Gn35U6Am86Rw2Wyx3yj0EZaFYBXCdWecRCgaXqnUJr6eWJKeiVp8vK4ukR7WLrmBCvSFdoY/JPRKKPm/OAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b57d077f9354fc55661e9b9b4d076820cb18f2630dd6223ac4ff6810089e6aca","last_reissued_at":"2026-07-05T04:02:01.783878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:01.783878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingming Liu, Liang Wang, Wei Zhao, Zhuoyu Wei","submitted_at":"2022-03-04T07:36:30Z","abstract_excerpt":"Knowledge graph completion (KGC) aims to reason over known facts and infer the missing links. Text-based methods such as KGBERT (Yao et al., 2019) learn entity representations from natural language descriptions, and have the potential for inductive KGC. However, the performance of text-based methods still largely lag behind graph embedding-based methods like TransE (Bordes et al., 2013) and RotatE (Sun et al., 2019b). In this paper, we identify that the key issue is efficient contrastive learning. To improve the learning efficiency, we introduce three types of negatives: in-batch negatives, pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02167","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/2203.02167/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":"2203.02167","created_at":"2026-07-05T04:02:01.783929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.02167v1","created_at":"2026-07-05T04:02:01.783929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02167","created_at":"2026-07-05T04:02:01.783929+00:00"},{"alias_kind":"pith_short_12","alias_value":"WV6QO74TKT6F","created_at":"2026-07-05T04:02:01.783929+00:00"},{"alias_kind":"pith_short_16","alias_value":"WV6QO74TKT6FKZQ6","created_at":"2026-07-05T04:02:01.783929+00:00"},{"alias_kind":"pith_short_8","alias_value":"WV6QO74T","created_at":"2026-07-05T04:02:01.783929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04118","citing_title":"AgREE: Agentic Reasoning for Knowledge Graph Completion on Emerging Entities","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WV6QO74TKT6FKZQ6TONU2B3IED","json":"https://pith.science/pith/WV6QO74TKT6FKZQ6TONU2B3IED.json","graph_json":"https://pith.science/api/pith-number/WV6QO74TKT6FKZQ6TONU2B3IED/graph.json","events_json":"https://pith.science/api/pith-number/WV6QO74TKT6FKZQ6TONU2B3IED/events.json","paper":"https://pith.science/paper/WV6QO74T"},"agent_actions":{"view_html":"https://pith.science/pith/WV6QO74TKT6FKZQ6TONU2B3IED","download_json":"https://pith.science/pith/WV6QO74TKT6FKZQ6TONU2B3IED.json","view_paper":"https://pith.science/paper/WV6QO74T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.02167&json=true","fetch_graph":"https://pith.science/api/pith-number/WV6QO74TKT6FKZQ6TONU2B3IED/graph.json","fetch_events":"https://pith.science/api/pith-number/WV6QO74TKT6FKZQ6TONU2B3IED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WV6QO74TKT6FKZQ6TONU2B3IED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WV6QO74TKT6FKZQ6TONU2B3IED/action/storage_attestation","attest_author":"https://pith.science/pith/WV6QO74TKT6FKZQ6TONU2B3IED/action/author_attestation","sign_citation":"https://pith.science/pith/WV6QO74TKT6FKZQ6TONU2B3IED/action/citation_signature","submit_replication":"https://pith.science/pith/WV6QO74TKT6FKZQ6TONU2B3IED/action/replication_record"}},"created_at":"2026-07-05T04:02:01.783929+00:00","updated_at":"2026-07-05T04:02:01.783929+00:00"}