{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GPNPCGFLFMXBFDP6LLFLDZMLA3","short_pith_number":"pith:GPNPCGFL","schema_version":"1.0","canonical_sha256":"33daf118ab2b2e128dfe5acab1e58b06d6b0198375b6f0af9e0064160d430a8b","source":{"kind":"arxiv","id":"2311.09122","version":3},"attestation_state":"computed","paper":{"title":"Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arij Riabi, Barbara Plank, B\\\"orje F. Karlsson, Hila Gonen, Joseph Marvin Imperial, LJ Miranda, Marek \\v{S}uppa, Nikola Ljube\\v{s}i\\'c, Peiqin Lin, Shuheng Liu, Stephen Mayhew, Terra Blevins, Yuval Pinter","submitted_at":"2023-11-15T17:09:54Z","abstract_excerpt":"We introduce Universal NER (UNER), an open, community-driven project to develop gold-standard NER benchmarks in many languages. The overarching goal of UNER is to provide high-quality, cross-lingually consistent annotations to facilitate and standardize multilingual NER research. UNER v1 contains 18 datasets annotated with named entities in a cross-lingual consistent schema across 12 diverse languages. In this paper, we detail the dataset creation and composition of UNER; we also provide initial modeling baselines on both in-language and cross-lingual learning settings. We release the data, co"},"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":"2311.09122","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T17:09:54Z","cross_cats_sorted":[],"title_canon_sha256":"4a7f82f195060109ecfdc17121a9dd42085263cdae90a56013f57388897b8a98","abstract_canon_sha256":"15904d92bb446c3d9e3b39e02ae7abe41db60b7a0bec903bb36281935be80a98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:04.261357Z","signature_b64":"6JAln5GC0bqO9PjoYn/Cf+myZf7pqXAhJIxRLlrJV5jySe246DRhGClpCsaWyhOZPSMw6NKu/WnB3RZLN7DAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33daf118ab2b2e128dfe5acab1e58b06d6b0198375b6f0af9e0064160d430a8b","last_reissued_at":"2026-07-05T08:38:04.260931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:04.260931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arij Riabi, Barbara Plank, B\\\"orje F. Karlsson, Hila Gonen, Joseph Marvin Imperial, LJ Miranda, Marek \\v{S}uppa, Nikola Ljube\\v{s}i\\'c, Peiqin Lin, Shuheng Liu, Stephen Mayhew, Terra Blevins, Yuval Pinter","submitted_at":"2023-11-15T17:09:54Z","abstract_excerpt":"We introduce Universal NER (UNER), an open, community-driven project to develop gold-standard NER benchmarks in many languages. The overarching goal of UNER is to provide high-quality, cross-lingually consistent annotations to facilitate and standardize multilingual NER research. UNER v1 contains 18 datasets annotated with named entities in a cross-lingual consistent schema across 12 diverse languages. In this paper, we detail the dataset creation and composition of UNER; we also provide initial modeling baselines on both in-language and cross-lingual learning settings. We release the data, co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09122","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/2311.09122/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":"2311.09122","created_at":"2026-07-05T08:38:04.260993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09122v3","created_at":"2026-07-05T08:38:04.260993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09122","created_at":"2026-07-05T08:38:04.260993+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPNPCGFLFMXB","created_at":"2026-07-05T08:38:04.260993+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPNPCGFLFMXBFDP6","created_at":"2026-07-05T08:38:04.260993+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPNPCGFL","created_at":"2026-07-05T08:38:04.260993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPNPCGFLFMXBFDP6LLFLDZMLA3","json":"https://pith.science/pith/GPNPCGFLFMXBFDP6LLFLDZMLA3.json","graph_json":"https://pith.science/api/pith-number/GPNPCGFLFMXBFDP6LLFLDZMLA3/graph.json","events_json":"https://pith.science/api/pith-number/GPNPCGFLFMXBFDP6LLFLDZMLA3/events.json","paper":"https://pith.science/paper/GPNPCGFL"},"agent_actions":{"view_html":"https://pith.science/pith/GPNPCGFLFMXBFDP6LLFLDZMLA3","download_json":"https://pith.science/pith/GPNPCGFLFMXBFDP6LLFLDZMLA3.json","view_paper":"https://pith.science/paper/GPNPCGFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09122&json=true","fetch_graph":"https://pith.science/api/pith-number/GPNPCGFLFMXBFDP6LLFLDZMLA3/graph.json","fetch_events":"https://pith.science/api/pith-number/GPNPCGFLFMXBFDP6LLFLDZMLA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPNPCGFLFMXBFDP6LLFLDZMLA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPNPCGFLFMXBFDP6LLFLDZMLA3/action/storage_attestation","attest_author":"https://pith.science/pith/GPNPCGFLFMXBFDP6LLFLDZMLA3/action/author_attestation","sign_citation":"https://pith.science/pith/GPNPCGFLFMXBFDP6LLFLDZMLA3/action/citation_signature","submit_replication":"https://pith.science/pith/GPNPCGFLFMXBFDP6LLFLDZMLA3/action/replication_record"}},"created_at":"2026-07-05T08:38:04.260993+00:00","updated_at":"2026-07-05T08:38:04.260993+00:00"}