{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MHRPZI4BQ5JJPAGTI5MDASZTDL","short_pith_number":"pith:MHRPZI4B","schema_version":"1.0","canonical_sha256":"61e2fca38187529780d34758304b331ad009d15fe91b61687eb23787870d264e","source":{"kind":"arxiv","id":"2602.04729","version":2},"attestation_state":"computed","paper":{"title":"\"Be My Cheese?\": Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Casey Ford, Cory Holland, Jennifer Barajas, Madison Van Doren, Riley VanMeter","submitted_at":"2026-02-04T16:35:48Z","abstract_excerpt":"We present a large-scale human evaluation benchmark for assessing cultural localisation in machine translation produced by state-of-the-art multilingual large language models (LLMs). Existing MT benchmarks emphasise token-level and grammatical accuracy, but often overlook the pragmatic and culturally grounded competencies required for real-world localisation. Building on a pilot study of 87 translations across 20 languages, we evaluate 7 multilingual LLMs across 15 target languages with 5 native-speaker raters per language. Each rater scored both full-text translations and segment-level instan"},"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":"2602.04729","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-04T16:35:48Z","cross_cats_sorted":[],"title_canon_sha256":"92c75ac858f8ced9a429e054170242f26694220e1aa02ed7ce0e93f89e17d766","abstract_canon_sha256":"eb41e97cffd0dc1a53321398fe239cf0b7669dbfeae76ac5fddc77c50f375821"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:03.364701Z","signature_b64":"cbF1Y87O5Vs/pYhSOzR55M9Plm1xltvYmzXwwYuWWw7SfNHtgrz3ptZrTKdbapM0+UvP2oa6kXzRzX8ibPTYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61e2fca38187529780d34758304b331ad009d15fe91b61687eb23787870d264e","last_reissued_at":"2026-05-29T01:05:03.363778Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:03.363778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Be My Cheese?\": Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Casey Ford, Cory Holland, Jennifer Barajas, Madison Van Doren, Riley VanMeter","submitted_at":"2026-02-04T16:35:48Z","abstract_excerpt":"We present a large-scale human evaluation benchmark for assessing cultural localisation in machine translation produced by state-of-the-art multilingual large language models (LLMs). Existing MT benchmarks emphasise token-level and grammatical accuracy, but often overlook the pragmatic and culturally grounded competencies required for real-world localisation. Building on a pilot study of 87 translations across 20 languages, we evaluate 7 multilingual LLMs across 15 target languages with 5 native-speaker raters per language. Each rater scored both full-text translations and segment-level instan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04729","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/2602.04729/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":"2602.04729","created_at":"2026-05-29T01:05:03.363909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.04729v2","created_at":"2026-05-29T01:05:03.363909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04729","created_at":"2026-05-29T01:05:03.363909+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHRPZI4BQ5JJ","created_at":"2026-05-29T01:05:03.363909+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHRPZI4BQ5JJPAGT","created_at":"2026-05-29T01:05:03.363909+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHRPZI4B","created_at":"2026-05-29T01:05:03.363909+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/MHRPZI4BQ5JJPAGTI5MDASZTDL","json":"https://pith.science/pith/MHRPZI4BQ5JJPAGTI5MDASZTDL.json","graph_json":"https://pith.science/api/pith-number/MHRPZI4BQ5JJPAGTI5MDASZTDL/graph.json","events_json":"https://pith.science/api/pith-number/MHRPZI4BQ5JJPAGTI5MDASZTDL/events.json","paper":"https://pith.science/paper/MHRPZI4B"},"agent_actions":{"view_html":"https://pith.science/pith/MHRPZI4BQ5JJPAGTI5MDASZTDL","download_json":"https://pith.science/pith/MHRPZI4BQ5JJPAGTI5MDASZTDL.json","view_paper":"https://pith.science/paper/MHRPZI4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.04729&json=true","fetch_graph":"https://pith.science/api/pith-number/MHRPZI4BQ5JJPAGTI5MDASZTDL/graph.json","fetch_events":"https://pith.science/api/pith-number/MHRPZI4BQ5JJPAGTI5MDASZTDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHRPZI4BQ5JJPAGTI5MDASZTDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHRPZI4BQ5JJPAGTI5MDASZTDL/action/storage_attestation","attest_author":"https://pith.science/pith/MHRPZI4BQ5JJPAGTI5MDASZTDL/action/author_attestation","sign_citation":"https://pith.science/pith/MHRPZI4BQ5JJPAGTI5MDASZTDL/action/citation_signature","submit_replication":"https://pith.science/pith/MHRPZI4BQ5JJPAGTI5MDASZTDL/action/replication_record"}},"created_at":"2026-05-29T01:05:03.363909+00:00","updated_at":"2026-05-29T01:05:03.363909+00:00"}