{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YILNUVZROKMO23C4BY6A77VF3I","short_pith_number":"pith:YILNUVZR","schema_version":"1.0","canonical_sha256":"c216da57317298ed6c5c0e3c0ffea5da03dfd8b0cbd65123a886fb3c77273738","source":{"kind":"arxiv","id":"2405.09496","version":1},"attestation_state":"computed","paper":{"title":"ParaNames 1.0: Creating an Entity Name Corpus for 400+ Languages using Wikidata","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Constantine Lignos, Jonne S\\\"alev\\\"a","submitted_at":"2024-05-15T16:44:54Z","abstract_excerpt":"We introduce ParaNames, a massively multilingual parallel name resource consisting of 140 million names spanning over 400 languages. Names are provided for 16.8 million entities, and each entity is mapped from a complex type hierarchy to a standard type (PER/LOC/ORG). Using Wikidata as a source, we create the largest resource of this type to date. We describe our approach to filtering and standardizing the data to provide the best quality possible. ParaNames is useful for multilingual language processing, both in defining tasks for name translation/transliteration and as supplementary data for"},"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":"2405.09496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-15T16:44:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4688f33aa2fd892c3e01542fd710d790bfff09b429c7d5b49495913801ad644a","abstract_canon_sha256":"210e2a4a0d19ea0f66b76eed7f412e10357461edb5f311c8e602a3bb8148fe7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:31.194420Z","signature_b64":"erLQaT/ITDWQjsnJrYr/R8k+RompKE05/pEdKIDC67jcujD/3R9ZViXhEQmRTgmuRnPCD2uKNdSTWl7iS2C5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c216da57317298ed6c5c0e3c0ffea5da03dfd8b0cbd65123a886fb3c77273738","last_reissued_at":"2026-07-05T08:19:31.194033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:31.194033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParaNames 1.0: Creating an Entity Name Corpus for 400+ Languages using Wikidata","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Constantine Lignos, Jonne S\\\"alev\\\"a","submitted_at":"2024-05-15T16:44:54Z","abstract_excerpt":"We introduce ParaNames, a massively multilingual parallel name resource consisting of 140 million names spanning over 400 languages. Names are provided for 16.8 million entities, and each entity is mapped from a complex type hierarchy to a standard type (PER/LOC/ORG). Using Wikidata as a source, we create the largest resource of this type to date. We describe our approach to filtering and standardizing the data to provide the best quality possible. ParaNames is useful for multilingual language processing, both in defining tasks for name translation/transliteration and as supplementary data for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09496","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/2405.09496/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":"2405.09496","created_at":"2026-07-05T08:19:31.194088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.09496v1","created_at":"2026-07-05T08:19:31.194088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09496","created_at":"2026-07-05T08:19:31.194088+00:00"},{"alias_kind":"pith_short_12","alias_value":"YILNUVZROKMO","created_at":"2026-07-05T08:19:31.194088+00:00"},{"alias_kind":"pith_short_16","alias_value":"YILNUVZROKMO23C4","created_at":"2026-07-05T08:19:31.194088+00:00"},{"alias_kind":"pith_short_8","alias_value":"YILNUVZR","created_at":"2026-07-05T08:19:31.194088+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/YILNUVZROKMO23C4BY6A77VF3I","json":"https://pith.science/pith/YILNUVZROKMO23C4BY6A77VF3I.json","graph_json":"https://pith.science/api/pith-number/YILNUVZROKMO23C4BY6A77VF3I/graph.json","events_json":"https://pith.science/api/pith-number/YILNUVZROKMO23C4BY6A77VF3I/events.json","paper":"https://pith.science/paper/YILNUVZR"},"agent_actions":{"view_html":"https://pith.science/pith/YILNUVZROKMO23C4BY6A77VF3I","download_json":"https://pith.science/pith/YILNUVZROKMO23C4BY6A77VF3I.json","view_paper":"https://pith.science/paper/YILNUVZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.09496&json=true","fetch_graph":"https://pith.science/api/pith-number/YILNUVZROKMO23C4BY6A77VF3I/graph.json","fetch_events":"https://pith.science/api/pith-number/YILNUVZROKMO23C4BY6A77VF3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YILNUVZROKMO23C4BY6A77VF3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YILNUVZROKMO23C4BY6A77VF3I/action/storage_attestation","attest_author":"https://pith.science/pith/YILNUVZROKMO23C4BY6A77VF3I/action/author_attestation","sign_citation":"https://pith.science/pith/YILNUVZROKMO23C4BY6A77VF3I/action/citation_signature","submit_replication":"https://pith.science/pith/YILNUVZROKMO23C4BY6A77VF3I/action/replication_record"}},"created_at":"2026-07-05T08:19:31.194088+00:00","updated_at":"2026-07-05T08:19:31.194088+00:00"}