{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P3JRXDDIH2IPFR66MZAUDBX2UW","short_pith_number":"pith:P3JRXDDI","schema_version":"1.0","canonical_sha256":"7ed31b8c683e90f2c7de66414186faa58bbe32fc278661b7781484812cfc4fd3","source":{"kind":"arxiv","id":"2504.10356","version":2},"attestation_state":"computed","paper":{"title":"MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dieuwke Hupkes, Nikolay Bogoychev","submitted_at":"2025-04-14T16:05:59Z","abstract_excerpt":"We present MultiLoKo, a new benchmark for evaluating multilinguality in LLMs covering 31 languages. MultiLoKo consists of three partitions: a main partition consisting of 500 questions per language, separately sourced to be locally relevant to the specific language, and two translated partitions, containing human-authored translations from 30 non-English languages to English and vice versa. For comparison, we also release corresponding machine-authored translations. The data is equally distributed over two splits: a dev split and a blind, out-of-distribution test split. MultiLoKo can be used t"},"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":"2504.10356","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T16:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"5dcc330d419c63f5c092b639798c3d1a5f353725f392fc03fd1e08db30417d96","abstract_canon_sha256":"8c9bcc87997167ba9a48a8cef3ddff11b9af3551c1a413893af7921edaaaaec5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:18.283825Z","signature_b64":"tdDm0Y8XqItUgfvP31g8wZD4GNuLpi1xJrqpNHRpiRzxNBZKA8zxyZBdif5Ctc45pbxmQsVo1P2opHAL/DwfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ed31b8c683e90f2c7de66414186faa58bbe32fc278661b7781484812cfc4fd3","last_reissued_at":"2026-07-05T10:49:18.283335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:18.283335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dieuwke Hupkes, Nikolay Bogoychev","submitted_at":"2025-04-14T16:05:59Z","abstract_excerpt":"We present MultiLoKo, a new benchmark for evaluating multilinguality in LLMs covering 31 languages. MultiLoKo consists of three partitions: a main partition consisting of 500 questions per language, separately sourced to be locally relevant to the specific language, and two translated partitions, containing human-authored translations from 30 non-English languages to English and vice versa. For comparison, we also release corresponding machine-authored translations. The data is equally distributed over two splits: a dev split and a blind, out-of-distribution test split. MultiLoKo can be used t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10356","kind":"arxiv","version":2},"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/2504.10356/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":"2504.10356","created_at":"2026-07-05T10:49:18.283394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10356v2","created_at":"2026-07-05T10:49:18.283394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10356","created_at":"2026-07-05T10:49:18.283394+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3JRXDDIH2IP","created_at":"2026-07-05T10:49:18.283394+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3JRXDDIH2IPFR66","created_at":"2026-07-05T10:49:18.283394+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3JRXDDI","created_at":"2026-07-05T10:49:18.283394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00724","citing_title":"MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26293","citing_title":"CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30481","citing_title":"When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3JRXDDIH2IPFR66MZAUDBX2UW","json":"https://pith.science/pith/P3JRXDDIH2IPFR66MZAUDBX2UW.json","graph_json":"https://pith.science/api/pith-number/P3JRXDDIH2IPFR66MZAUDBX2UW/graph.json","events_json":"https://pith.science/api/pith-number/P3JRXDDIH2IPFR66MZAUDBX2UW/events.json","paper":"https://pith.science/paper/P3JRXDDI"},"agent_actions":{"view_html":"https://pith.science/pith/P3JRXDDIH2IPFR66MZAUDBX2UW","download_json":"https://pith.science/pith/P3JRXDDIH2IPFR66MZAUDBX2UW.json","view_paper":"https://pith.science/paper/P3JRXDDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10356&json=true","fetch_graph":"https://pith.science/api/pith-number/P3JRXDDIH2IPFR66MZAUDBX2UW/graph.json","fetch_events":"https://pith.science/api/pith-number/P3JRXDDIH2IPFR66MZAUDBX2UW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3JRXDDIH2IPFR66MZAUDBX2UW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3JRXDDIH2IPFR66MZAUDBX2UW/action/storage_attestation","attest_author":"https://pith.science/pith/P3JRXDDIH2IPFR66MZAUDBX2UW/action/author_attestation","sign_citation":"https://pith.science/pith/P3JRXDDIH2IPFR66MZAUDBX2UW/action/citation_signature","submit_replication":"https://pith.science/pith/P3JRXDDIH2IPFR66MZAUDBX2UW/action/replication_record"}},"created_at":"2026-07-05T10:49:18.283394+00:00","updated_at":"2026-07-05T10:49:18.283394+00:00"}