{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XNLEITJVAHVTDHRG76EJUV5RDB","short_pith_number":"pith:XNLEITJV","schema_version":"1.0","canonical_sha256":"bb56444d3501eb319e26ff889a57b1186b372bcd6918fcd0523da7f6c3d25765","source":{"kind":"arxiv","id":"2402.14273","version":1},"attestation_state":"computed","paper":{"title":"Can Language Models Act as Knowledge Bases at Scale?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qiyuan He, Wenya Wang, Yizhong Wang","submitted_at":"2024-02-22T04:20:14Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable proficiency in understanding and generating responses to complex queries through large-scale pre-training. However, the efficacy of these models in memorizing and reasoning among large-scale structured knowledge, especially world knowledge that explicitly covers abundant factual information remains questionable. Addressing this gap, our research investigates whether LLMs can effectively store, recall, and reason with knowledge on a large scale comparable to latest knowledge bases (KBs) such as Wikidata. Specifically, we focus on three 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":"2402.14273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T04:20:14Z","cross_cats_sorted":[],"title_canon_sha256":"564485daae935565182c9849b46459adedfa33784ea9346fbf87ee01f1027ece","abstract_canon_sha256":"5631c5621739a3280c8f6606a2db535c06d60f12f34a15e9d45bdb7827f3fc2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:07.956203Z","signature_b64":"0GJOkjHzT/biQOy6T82EmSpHqPkHHocW9NK/uQfMbjuSEYLfMJxcvTrVC35Dms5eMIAfG5BaDLZoycs9Q3m6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb56444d3501eb319e26ff889a57b1186b372bcd6918fcd0523da7f6c3d25765","last_reissued_at":"2026-07-05T07:48:07.955711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:07.955711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Language Models Act as Knowledge Bases at Scale?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qiyuan He, Wenya Wang, Yizhong Wang","submitted_at":"2024-02-22T04:20:14Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable proficiency in understanding and generating responses to complex queries through large-scale pre-training. However, the efficacy of these models in memorizing and reasoning among large-scale structured knowledge, especially world knowledge that explicitly covers abundant factual information remains questionable. Addressing this gap, our research investigates whether LLMs can effectively store, recall, and reason with knowledge on a large scale comparable to latest knowledge bases (KBs) such as Wikidata. Specifically, we focus on three c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14273","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/2402.14273/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":"2402.14273","created_at":"2026-07-05T07:48:07.955772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14273v1","created_at":"2026-07-05T07:48:07.955772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14273","created_at":"2026-07-05T07:48:07.955772+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNLEITJVAHVT","created_at":"2026-07-05T07:48:07.955772+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNLEITJVAHVTDHRG","created_at":"2026-07-05T07:48:07.955772+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNLEITJV","created_at":"2026-07-05T07:48:07.955772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNLEITJVAHVTDHRG76EJUV5RDB","json":"https://pith.science/pith/XNLEITJVAHVTDHRG76EJUV5RDB.json","graph_json":"https://pith.science/api/pith-number/XNLEITJVAHVTDHRG76EJUV5RDB/graph.json","events_json":"https://pith.science/api/pith-number/XNLEITJVAHVTDHRG76EJUV5RDB/events.json","paper":"https://pith.science/paper/XNLEITJV"},"agent_actions":{"view_html":"https://pith.science/pith/XNLEITJVAHVTDHRG76EJUV5RDB","download_json":"https://pith.science/pith/XNLEITJVAHVTDHRG76EJUV5RDB.json","view_paper":"https://pith.science/paper/XNLEITJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14273&json=true","fetch_graph":"https://pith.science/api/pith-number/XNLEITJVAHVTDHRG76EJUV5RDB/graph.json","fetch_events":"https://pith.science/api/pith-number/XNLEITJVAHVTDHRG76EJUV5RDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNLEITJVAHVTDHRG76EJUV5RDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNLEITJVAHVTDHRG76EJUV5RDB/action/storage_attestation","attest_author":"https://pith.science/pith/XNLEITJVAHVTDHRG76EJUV5RDB/action/author_attestation","sign_citation":"https://pith.science/pith/XNLEITJVAHVTDHRG76EJUV5RDB/action/citation_signature","submit_replication":"https://pith.science/pith/XNLEITJVAHVTDHRG76EJUV5RDB/action/replication_record"}},"created_at":"2026-07-05T07:48:07.955772+00:00","updated_at":"2026-07-05T07:48:07.955772+00:00"}