{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BSALIJ3K6XPWHIMZ5Q5M3RM2JS","short_pith_number":"pith:BSALIJ3K","schema_version":"1.0","canonical_sha256":"0c80b4276af5df63a199ec3acdc59a4c8efea01d5771210afa6acecbc9575305","source":{"kind":"arxiv","id":"2206.12617","version":3},"attestation_state":"computed","paper":{"title":"Language Models as Knowledge Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiaqing Liang, Qianyu He, Xintao Wang, Yanghua Xiao","submitted_at":"2022-06-25T10:39:12Z","abstract_excerpt":"Knowledge embeddings (KE) represent a knowledge graph (KG) by embedding entities and relations into continuous vector spaces. Existing methods are mainly structure-based or description-based. Structure-based methods learn representations that preserve the inherent structure of KGs. They cannot well represent abundant long-tail entities in real-world KGs with limited structural information. Description-based methods leverage textual information and language models. Prior approaches in this direction barely outperform structure-based ones, and suffer from problems like expensive negative samplin"},"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":"2206.12617","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-25T10:39:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"09365e91623fd12c464a0b37c75aee4d3b4a665222c101a4a82d0d49147a8a3a","abstract_canon_sha256":"2b5e6a3b985bfe1fa867903f7ba4cc04e55784321390197db9d5f735a9f3f271"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:57.687265Z","signature_b64":"YH5djDlMm8xtKUeRHiENR/6r7+pfrZfOT99Gd7jfcgejsLzShjbKgiVORW2VurFvCIBxMiIyAEz2jrawtLe7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c80b4276af5df63a199ec3acdc59a4c8efea01d5771210afa6acecbc9575305","last_reissued_at":"2026-07-05T06:25:57.686904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:57.686904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models as Knowledge Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiaqing Liang, Qianyu He, Xintao Wang, Yanghua Xiao","submitted_at":"2022-06-25T10:39:12Z","abstract_excerpt":"Knowledge embeddings (KE) represent a knowledge graph (KG) by embedding entities and relations into continuous vector spaces. Existing methods are mainly structure-based or description-based. Structure-based methods learn representations that preserve the inherent structure of KGs. They cannot well represent abundant long-tail entities in real-world KGs with limited structural information. Description-based methods leverage textual information and language models. Prior approaches in this direction barely outperform structure-based ones, and suffer from problems like expensive negative samplin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12617","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/2206.12617/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":"2206.12617","created_at":"2026-07-05T06:25:57.686958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.12617v3","created_at":"2026-07-05T06:25:57.686958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12617","created_at":"2026-07-05T06:25:57.686958+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSALIJ3K6XPW","created_at":"2026-07-05T06:25:57.686958+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSALIJ3K6XPWHIMZ","created_at":"2026-07-05T06:25:57.686958+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSALIJ3K","created_at":"2026-07-05T06:25:57.686958+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":80,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSALIJ3K6XPWHIMZ5Q5M3RM2JS","json":"https://pith.science/pith/BSALIJ3K6XPWHIMZ5Q5M3RM2JS.json","graph_json":"https://pith.science/api/pith-number/BSALIJ3K6XPWHIMZ5Q5M3RM2JS/graph.json","events_json":"https://pith.science/api/pith-number/BSALIJ3K6XPWHIMZ5Q5M3RM2JS/events.json","paper":"https://pith.science/paper/BSALIJ3K"},"agent_actions":{"view_html":"https://pith.science/pith/BSALIJ3K6XPWHIMZ5Q5M3RM2JS","download_json":"https://pith.science/pith/BSALIJ3K6XPWHIMZ5Q5M3RM2JS.json","view_paper":"https://pith.science/paper/BSALIJ3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.12617&json=true","fetch_graph":"https://pith.science/api/pith-number/BSALIJ3K6XPWHIMZ5Q5M3RM2JS/graph.json","fetch_events":"https://pith.science/api/pith-number/BSALIJ3K6XPWHIMZ5Q5M3RM2JS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSALIJ3K6XPWHIMZ5Q5M3RM2JS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSALIJ3K6XPWHIMZ5Q5M3RM2JS/action/storage_attestation","attest_author":"https://pith.science/pith/BSALIJ3K6XPWHIMZ5Q5M3RM2JS/action/author_attestation","sign_citation":"https://pith.science/pith/BSALIJ3K6XPWHIMZ5Q5M3RM2JS/action/citation_signature","submit_replication":"https://pith.science/pith/BSALIJ3K6XPWHIMZ5Q5M3RM2JS/action/replication_record"}},"created_at":"2026-07-05T06:25:57.686958+00:00","updated_at":"2026-07-05T06:25:57.686958+00:00"}