{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E3WVRJ45VVX24PDLIVFUNHYCVE","short_pith_number":"pith:E3WVRJ45","schema_version":"1.0","canonical_sha256":"26ed58a79dad6fae3c6b454b469f02a90af9f5ac72f043ba72afe4020dfaa72f","source":{"kind":"arxiv","id":"2204.06031","version":1},"attestation_state":"computed","paper":{"title":"A Review on Language Models as Knowledge Bases","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Asli Celikyilmaz, Badr AlKhamissi, Marjan Ghazvininejad, Millicent Li, Mona Diab","submitted_at":"2022-04-12T18:35:23Z","abstract_excerpt":"Recently, there has been a surge of interest in the NLP community on the use of pretrained Language Models (LMs) as Knowledge Bases (KBs). Researchers have shown that LMs trained on a sufficiently large (web) corpus will encode a significant amount of knowledge implicitly in its parameters. The resulting LM can be probed for different kinds of knowledge and thus acting as a KB. This has a major advantage over traditional KBs in that this method requires no human supervision. In this paper, we present a set of aspects that we deem a LM should have to fully act as a KB, and review the recent lit"},"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":"2204.06031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T18:35:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"deef8a9e75a1ab705986472d4d1fe85885d9a24134fc1a4b7760f5371786a36a","abstract_canon_sha256":"92bbb76f5d88c55a2da1f01e26f92317307f9f780b4e85767024f84b27ed8284"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:29.047891Z","signature_b64":"hdfqNNthgCTKdAgB+yStERXA2lzJuiuhoVhYorAQ26WpjzDEMELwW/usjGUtYhw0rFAD3t3q4wfzH5+qbJeJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26ed58a79dad6fae3c6b454b469f02a90af9f5ac72f043ba72afe4020dfaa72f","last_reissued_at":"2026-07-05T04:14:29.047481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:29.047481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Review on Language Models as Knowledge Bases","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Asli Celikyilmaz, Badr AlKhamissi, Marjan Ghazvininejad, Millicent Li, Mona Diab","submitted_at":"2022-04-12T18:35:23Z","abstract_excerpt":"Recently, there has been a surge of interest in the NLP community on the use of pretrained Language Models (LMs) as Knowledge Bases (KBs). Researchers have shown that LMs trained on a sufficiently large (web) corpus will encode a significant amount of knowledge implicitly in its parameters. The resulting LM can be probed for different kinds of knowledge and thus acting as a KB. This has a major advantage over traditional KBs in that this method requires no human supervision. In this paper, we present a set of aspects that we deem a LM should have to fully act as a KB, and review the recent lit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06031","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/2204.06031/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":"2204.06031","created_at":"2026-07-05T04:14:29.047544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.06031v1","created_at":"2026-07-05T04:14:29.047544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06031","created_at":"2026-07-05T04:14:29.047544+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3WVRJ45VVX2","created_at":"2026-07-05T04:14:29.047544+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3WVRJ45VVX24PDL","created_at":"2026-07-05T04:14:29.047544+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3WVRJ45","created_at":"2026-07-05T04:14:29.047544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00570","citing_title":"Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2210.07229","citing_title":"Mass-Editing Memory in a Transformer","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02765","citing_title":"U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E3WVRJ45VVX24PDLIVFUNHYCVE","json":"https://pith.science/pith/E3WVRJ45VVX24PDLIVFUNHYCVE.json","graph_json":"https://pith.science/api/pith-number/E3WVRJ45VVX24PDLIVFUNHYCVE/graph.json","events_json":"https://pith.science/api/pith-number/E3WVRJ45VVX24PDLIVFUNHYCVE/events.json","paper":"https://pith.science/paper/E3WVRJ45"},"agent_actions":{"view_html":"https://pith.science/pith/E3WVRJ45VVX24PDLIVFUNHYCVE","download_json":"https://pith.science/pith/E3WVRJ45VVX24PDLIVFUNHYCVE.json","view_paper":"https://pith.science/paper/E3WVRJ45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.06031&json=true","fetch_graph":"https://pith.science/api/pith-number/E3WVRJ45VVX24PDLIVFUNHYCVE/graph.json","fetch_events":"https://pith.science/api/pith-number/E3WVRJ45VVX24PDLIVFUNHYCVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3WVRJ45VVX24PDLIVFUNHYCVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3WVRJ45VVX24PDLIVFUNHYCVE/action/storage_attestation","attest_author":"https://pith.science/pith/E3WVRJ45VVX24PDLIVFUNHYCVE/action/author_attestation","sign_citation":"https://pith.science/pith/E3WVRJ45VVX24PDLIVFUNHYCVE/action/citation_signature","submit_replication":"https://pith.science/pith/E3WVRJ45VVX24PDLIVFUNHYCVE/action/replication_record"}},"created_at":"2026-07-05T04:14:29.047544+00:00","updated_at":"2026-07-05T04:14:29.047544+00:00"}