{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MQJ2UJJU2LGF26IRQQBIDLAITM","short_pith_number":"pith:MQJ2UJJU","schema_version":"1.0","canonical_sha256":"6413aa2534d2cc5d7911840281ac089b1585741626530a73f5321e735418eed0","source":{"kind":"arxiv","id":"2205.02832","version":1},"attestation_state":"computed","paper":{"title":"Entity Cloze By Date: What LMs Know About Unseen Entities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Greg Durrett, Michael J.Q. Zhang, Yasumasa Onoe","submitted_at":"2022-05-05T17:59:31Z","abstract_excerpt":"Language models (LMs) are typically trained once on a large-scale corpus and used for years without being updated. However, in a dynamic world, new entities constantly arise. We propose a framework to analyze what LMs can infer about new entities that did not exist when the LMs were pretrained. We derive a dataset of entities indexed by their origination date and paired with their English Wikipedia articles, from which we can find sentences about each entity. We evaluate LMs' perplexity on masked spans within these sentences. We show that models more informed about the entities, such as those "},"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":"2205.02832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-05T17:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"e438a950044f16ad88ae5e0daedf03e95dcd3d0e847ddc7e41eef42c2da0f5fe","abstract_canon_sha256":"6cde50c4188a75cf773f060b094d4e9c00495faac8a49abe63495390578ecfff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:41.378364Z","signature_b64":"H8x03us2EsbO0HD+oz8arp9wmQfaS9duxPvV61J/jqiJm4kqhmzyyL2DbPaFzbG729Fy3oUQmz1Ptyp2b1YaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6413aa2534d2cc5d7911840281ac089b1585741626530a73f5321e735418eed0","last_reissued_at":"2026-07-05T04:20:41.377780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:41.377780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entity Cloze By Date: What LMs Know About Unseen Entities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eunsol Choi, Greg Durrett, Michael J.Q. Zhang, Yasumasa Onoe","submitted_at":"2022-05-05T17:59:31Z","abstract_excerpt":"Language models (LMs) are typically trained once on a large-scale corpus and used for years without being updated. However, in a dynamic world, new entities constantly arise. We propose a framework to analyze what LMs can infer about new entities that did not exist when the LMs were pretrained. We derive a dataset of entities indexed by their origination date and paired with their English Wikipedia articles, from which we can find sentences about each entity. We evaluate LMs' perplexity on masked spans within these sentences. We show that models more informed about the entities, such as those "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02832","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/2205.02832/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":"2205.02832","created_at":"2026-07-05T04:20:41.377850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.02832v1","created_at":"2026-07-05T04:20:41.377850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02832","created_at":"2026-07-05T04:20:41.377850+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQJ2UJJU2LGF","created_at":"2026-07-05T04:20:41.377850+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQJ2UJJU2LGF26IR","created_at":"2026-07-05T04:20:41.377850+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQJ2UJJU","created_at":"2026-07-05T04:20:41.377850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.18473","citing_title":"Principled Detection of Hallucinations in Large Language Models via Multiple Testing","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM","json":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM.json","graph_json":"https://pith.science/api/pith-number/MQJ2UJJU2LGF26IRQQBIDLAITM/graph.json","events_json":"https://pith.science/api/pith-number/MQJ2UJJU2LGF26IRQQBIDLAITM/events.json","paper":"https://pith.science/paper/MQJ2UJJU"},"agent_actions":{"view_html":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM","download_json":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM.json","view_paper":"https://pith.science/paper/MQJ2UJJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.02832&json=true","fetch_graph":"https://pith.science/api/pith-number/MQJ2UJJU2LGF26IRQQBIDLAITM/graph.json","fetch_events":"https://pith.science/api/pith-number/MQJ2UJJU2LGF26IRQQBIDLAITM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/action/storage_attestation","attest_author":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/action/author_attestation","sign_citation":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/action/citation_signature","submit_replication":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/action/replication_record"}},"created_at":"2026-07-05T04:20:41.377850+00:00","updated_at":"2026-07-05T04:20:41.377850+00:00"}