{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JELNJLECOD66TV6WCDAZZULFZ5","short_pith_number":"pith:JELNJLEC","schema_version":"1.0","canonical_sha256":"4916d4ac8270fde9d7d610c19cd165cf74461adedaa1880dbaad1fe32580765b","source":{"kind":"arxiv","id":"2204.14211","version":3},"attestation_state":"computed","paper":{"title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changho Lee, Gyeonghun Kim, Janghoon Han, Joel Jang, Joongbo Shin, Minjoon Seo, Seonghyeon Ye, Sohee Yang","submitted_at":"2022-04-29T16:40:07Z","abstract_excerpt":"Language Models (LMs) become outdated as the world changes; they often fail to perform tasks requiring recent factual information which was absent or different during training, a phenomenon called temporal misalignment. This is especially a challenging problem because the research community still lacks a coherent dataset for assessing the adaptability of LMs to frequently-updated knowledge corpus such as Wikipedia. To this end, we introduce TemporalWiki, a lifelong benchmark for ever-evolving LMs that utilizes the difference between consecutive snapshots of English Wikipedia and English Wikida"},"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":"2204.14211","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-29T16:40:07Z","cross_cats_sorted":[],"title_canon_sha256":"6a1082cf793ed2e1619eab01606d09f8bb61110b6b6eba48396e889b43055546","abstract_canon_sha256":"2634d607ced572c71bae42f821775fba01e630f63612737d616971631f29623d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:11.645693Z","signature_b64":"f0PhczYX1tyKpuqK1sAPyHUOauAeTfrEiGuJ6Yr4xQryEA3YLqkXz+u7k0U9hLfW8o7R8NdjGpKBBKvo96QaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4916d4ac8270fde9d7d610c19cd165cf74461adedaa1880dbaad1fe32580765b","last_reissued_at":"2026-07-05T06:00:11.645167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:11.645167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changho Lee, Gyeonghun Kim, Janghoon Han, Joel Jang, Joongbo Shin, Minjoon Seo, Seonghyeon Ye, Sohee Yang","submitted_at":"2022-04-29T16:40:07Z","abstract_excerpt":"Language Models (LMs) become outdated as the world changes; they often fail to perform tasks requiring recent factual information which was absent or different during training, a phenomenon called temporal misalignment. This is especially a challenging problem because the research community still lacks a coherent dataset for assessing the adaptability of LMs to frequently-updated knowledge corpus such as Wikipedia. To this end, we introduce TemporalWiki, a lifelong benchmark for ever-evolving LMs that utilizes the difference between consecutive snapshots of English Wikipedia and English Wikida"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.14211","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/2204.14211/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":"2204.14211","created_at":"2026-07-05T06:00:11.645231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.14211v3","created_at":"2026-07-05T06:00:11.645231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.14211","created_at":"2026-07-05T06:00:11.645231+00:00"},{"alias_kind":"pith_short_12","alias_value":"JELNJLECOD66","created_at":"2026-07-05T06:00:11.645231+00:00"},{"alias_kind":"pith_short_16","alias_value":"JELNJLECOD66TV6W","created_at":"2026-07-05T06:00:11.645231+00:00"},{"alias_kind":"pith_short_8","alias_value":"JELNJLEC","created_at":"2026-07-05T06:00:11.645231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09550","citing_title":"InquiTree: Evaluating AI Agents in the Scientific Inquiry Loop with Paper-Derived Research Trees","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17183","citing_title":"LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JELNJLECOD66TV6WCDAZZULFZ5","json":"https://pith.science/pith/JELNJLECOD66TV6WCDAZZULFZ5.json","graph_json":"https://pith.science/api/pith-number/JELNJLECOD66TV6WCDAZZULFZ5/graph.json","events_json":"https://pith.science/api/pith-number/JELNJLECOD66TV6WCDAZZULFZ5/events.json","paper":"https://pith.science/paper/JELNJLEC"},"agent_actions":{"view_html":"https://pith.science/pith/JELNJLECOD66TV6WCDAZZULFZ5","download_json":"https://pith.science/pith/JELNJLECOD66TV6WCDAZZULFZ5.json","view_paper":"https://pith.science/paper/JELNJLEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.14211&json=true","fetch_graph":"https://pith.science/api/pith-number/JELNJLECOD66TV6WCDAZZULFZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/JELNJLECOD66TV6WCDAZZULFZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JELNJLECOD66TV6WCDAZZULFZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JELNJLECOD66TV6WCDAZZULFZ5/action/storage_attestation","attest_author":"https://pith.science/pith/JELNJLECOD66TV6WCDAZZULFZ5/action/author_attestation","sign_citation":"https://pith.science/pith/JELNJLECOD66TV6WCDAZZULFZ5/action/citation_signature","submit_replication":"https://pith.science/pith/JELNJLECOD66TV6WCDAZZULFZ5/action/replication_record"}},"created_at":"2026-07-05T06:00:11.645231+00:00","updated_at":"2026-07-05T06:00:11.645231+00:00"}