{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:N34FUPZKW7GG2XS4NEUBAU3DOY","short_pith_number":"pith:N34FUPZK","schema_version":"1.0","canonical_sha256":"6ef85a3f2ab7cc6d5e5c69281053637613deba07429e3d8d86596dbbb526bf8b","source":{"kind":"arxiv","id":"2204.05211","version":1},"attestation_state":"computed","paper":{"title":"Entities, Dates, and Languages: Zero-Shot on Historical Texts with T0","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher Akiki, Cl\\'ementine Fourrier, Daniel van Strien, Enrique Manjavacas, Francesco De Toni, Javier de la Rosa, Stefan Schweter","submitted_at":"2022-04-11T15:56:13Z","abstract_excerpt":"In this work, we explore whether the recently demonstrated zero-shot abilities of the T0 model extend to Named Entity Recognition for out-of-distribution languages and time periods. Using a historical newspaper corpus in 3 languages as test-bed, we use prompts to extract possible named entities. Our results show that a naive approach for prompt-based zero-shot multilingual Named Entity Recognition is error-prone, but highlights the potential of such an approach for historical languages lacking labeled datasets. Moreover, we also find that T0-like models can be probed to predict the publication"},"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":"2204.05211","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-11T15:56:13Z","cross_cats_sorted":[],"title_canon_sha256":"99af7e3930674febbb57179be3c8e31642dfd85c1326adf36cc2701f9c9bd3be","abstract_canon_sha256":"8161d86699bf895c0cec61283a9e2d06a14c700ff5b582ffe5c27f3fb1599dc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:18.574705Z","signature_b64":"dzaFDkeL9qgi5RaZWGr10HUHR2Tcxwvs6MjCtp0QPNGz3DCKR2gphp8RB3V6wmeAoUvGi3E5RnhMSnpHeLfqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef85a3f2ab7cc6d5e5c69281053637613deba07429e3d8d86596dbbb526bf8b","last_reissued_at":"2026-07-05T04:13:18.574047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:18.574047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entities, Dates, and Languages: Zero-Shot on Historical Texts with T0","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher Akiki, Cl\\'ementine Fourrier, Daniel van Strien, Enrique Manjavacas, Francesco De Toni, Javier de la Rosa, Stefan Schweter","submitted_at":"2022-04-11T15:56:13Z","abstract_excerpt":"In this work, we explore whether the recently demonstrated zero-shot abilities of the T0 model extend to Named Entity Recognition for out-of-distribution languages and time periods. Using a historical newspaper corpus in 3 languages as test-bed, we use prompts to extract possible named entities. Our results show that a naive approach for prompt-based zero-shot multilingual Named Entity Recognition is error-prone, but highlights the potential of such an approach for historical languages lacking labeled datasets. Moreover, we also find that T0-like models can be probed to predict the publication"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05211","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/2204.05211/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":"2204.05211","created_at":"2026-07-05T04:13:18.574129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05211v1","created_at":"2026-07-05T04:13:18.574129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05211","created_at":"2026-07-05T04:13:18.574129+00:00"},{"alias_kind":"pith_short_12","alias_value":"N34FUPZKW7GG","created_at":"2026-07-05T04:13:18.574129+00:00"},{"alias_kind":"pith_short_16","alias_value":"N34FUPZKW7GG2XS4","created_at":"2026-07-05T04:13:18.574129+00:00"},{"alias_kind":"pith_short_8","alias_value":"N34FUPZK","created_at":"2026-07-05T04:13:18.574129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04351","citing_title":"NER4all or Context is All You Need: Using LLMs for low-effort, high-performance NER on historical texts. A humanities informed approach","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N34FUPZKW7GG2XS4NEUBAU3DOY","json":"https://pith.science/pith/N34FUPZKW7GG2XS4NEUBAU3DOY.json","graph_json":"https://pith.science/api/pith-number/N34FUPZKW7GG2XS4NEUBAU3DOY/graph.json","events_json":"https://pith.science/api/pith-number/N34FUPZKW7GG2XS4NEUBAU3DOY/events.json","paper":"https://pith.science/paper/N34FUPZK"},"agent_actions":{"view_html":"https://pith.science/pith/N34FUPZKW7GG2XS4NEUBAU3DOY","download_json":"https://pith.science/pith/N34FUPZKW7GG2XS4NEUBAU3DOY.json","view_paper":"https://pith.science/paper/N34FUPZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05211&json=true","fetch_graph":"https://pith.science/api/pith-number/N34FUPZKW7GG2XS4NEUBAU3DOY/graph.json","fetch_events":"https://pith.science/api/pith-number/N34FUPZKW7GG2XS4NEUBAU3DOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N34FUPZKW7GG2XS4NEUBAU3DOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N34FUPZKW7GG2XS4NEUBAU3DOY/action/storage_attestation","attest_author":"https://pith.science/pith/N34FUPZKW7GG2XS4NEUBAU3DOY/action/author_attestation","sign_citation":"https://pith.science/pith/N34FUPZKW7GG2XS4NEUBAU3DOY/action/citation_signature","submit_replication":"https://pith.science/pith/N34FUPZKW7GG2XS4NEUBAU3DOY/action/replication_record"}},"created_at":"2026-07-05T04:13:18.574129+00:00","updated_at":"2026-07-05T04:13:18.574129+00:00"}