{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MQJ2UJJU2LGF26IRQQBIDLAITM","short_pith_number":"pith:MQJ2UJJU","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"},"canonical_sha256":"6413aa2534d2cc5d7911840281ac089b1585741626530a73f5321e735418eed0","source":{"kind":"arxiv","id":"2205.02832","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02832","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02832v1","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02832","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"MQJ2UJJU2LGF","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"MQJ2UJJU2LGF26IR","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"MQJ2UJJU","created_at":"2026-07-05T04:20:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MQJ2UJJU2LGF26IRQQBIDLAITM","target":"record","payload":{"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"},"canonical_sha256":"6413aa2534d2cc5d7911840281ac089b1585741626530a73f5321e735418eed0","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"},"source_kind":"arxiv","source_id":"2205.02832","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xr3iH0pkJLtwIK/msWGvwEyy/6pD6iOz+WmNyW9GHExafLv+uSuw4f/aRBtDRmjyRTXGzsHwblSu3Tpspo1ZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:35:47.705555Z"},"content_sha256":"7cb49e3324980539549095e3a642c14dddcf4c984235417c0cafad8fa82b4d55","schema_version":"1.0","event_id":"sha256:7cb49e3324980539549095e3a642c14dddcf4c984235417c0cafad8fa82b4d55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MQJ2UJJU2LGF26IRQQBIDLAITM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GhJV6Wc4mskAMQI+dhQsj8a0a/Blhb9yzobP0FoVrc2FLlIO8AEqnuo3e53t2JzVt4eaZ3StY8vnxlBMrivRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:35:47.706107Z"},"content_sha256":"0738b92633694e96440cc4f24dd5a4b88af834d3519861022d0103852217dcc8","schema_version":"1.0","event_id":"sha256:0738b92633694e96440cc4f24dd5a4b88af834d3519861022d0103852217dcc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/bundle.json","state_url":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T23:35:47Z","links":{"resolver":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM","bundle":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/bundle.json","state":"https://pith.science/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQJ2UJJU2LGF26IRQQBIDLAITM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MQJ2UJJU2LGF26IRQQBIDLAITM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6cde50c4188a75cf773f060b094d4e9c00495faac8a49abe63495390578ecfff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-05T17:59:31Z","title_canon_sha256":"e438a950044f16ad88ae5e0daedf03e95dcd3d0e847ddc7e41eef42c2da0f5fe"},"schema_version":"1.0","source":{"id":"2205.02832","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02832","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02832v1","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02832","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"MQJ2UJJU2LGF","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"MQJ2UJJU2LGF26IR","created_at":"2026-07-05T04:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"MQJ2UJJU","created_at":"2026-07-05T04:20:41Z"}],"graph_snapshots":[{"event_id":"sha256:0738b92633694e96440cc4f24dd5a4b88af834d3519861022d0103852217dcc8","target":"graph","created_at":"2026-07-05T04:20:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.02832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Eunsol Choi, Greg Durrett, Michael J.Q. Zhang, Yasumasa Onoe","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-05T17:59:31Z","title":"Entity Cloze By Date: What LMs Know About Unseen Entities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02832","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7cb49e3324980539549095e3a642c14dddcf4c984235417c0cafad8fa82b4d55","target":"record","created_at":"2026-07-05T04:20:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6cde50c4188a75cf773f060b094d4e9c00495faac8a49abe63495390578ecfff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-05T17:59:31Z","title_canon_sha256":"e438a950044f16ad88ae5e0daedf03e95dcd3d0e847ddc7e41eef42c2da0f5fe"},"schema_version":"1.0","source":{"id":"2205.02832","kind":"arxiv","version":1}},"canonical_sha256":"6413aa2534d2cc5d7911840281ac089b1585741626530a73f5321e735418eed0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6413aa2534d2cc5d7911840281ac089b1585741626530a73f5321e735418eed0","first_computed_at":"2026-07-05T04:20:41.377780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:41.377780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H8x03us2EsbO0HD+oz8arp9wmQfaS9duxPvV61J/jqiJm4kqhmzyyL2DbPaFzbG729Fy3oUQmz1Ptyp2b1YaAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:41.378364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.02832","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cb49e3324980539549095e3a642c14dddcf4c984235417c0cafad8fa82b4d55","sha256:0738b92633694e96440cc4f24dd5a4b88af834d3519861022d0103852217dcc8"],"state_sha256":"23d615683a5eed00471cbe691610891032dfa29e314dc36229c161e854d33454"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hdi+gnsCQt+HE+Ibg3lMiKwSiJ4tPgh/jU0K6ESWd1d+ttIlMkofP0Qo6lJn9nsgeCoEVhbzH7Ls5nZ/cZJKDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T23:35:47.709408Z","bundle_sha256":"a1bb8bbd57b830c83a68ea06a0ad31c41032454e56a032bee0fc8ccfd3b9d5bf"}}