{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z5OY7BJP56MGGHP7T6BEL76O5H","short_pith_number":"pith:Z5OY7BJP","schema_version":"1.0","canonical_sha256":"cf5d8f852fef98631dff9f8245ffcee9ca4b5b2024affd98cc190a628ac9a112","source":{"kind":"arxiv","id":"2502.12404","version":1},"attestation_state":"computed","paper":{"title":"WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alison Lui, Biao Zhang, Daniel Deutsch, Eleftheria Briakou, Elizabeth Salesky, Firas Trabelsi, Geza Kovacs, Isaac Caswell, Jason Riesa, Juraj Juraska, Mara Finkelstein, Markus Freitag, Parker Riley, Rebecca Galor, Ricardo Rei, Shruti Rijhwani, Stephanie Winkler","submitted_at":"2025-02-18T00:39:30Z","abstract_excerpt":"As large language models (LLM) become more and more capable in languages other than English, it is important to collect benchmark datasets in order to evaluate their multilingual performance, including on tasks like machine translation (MT). In this work, we extend the WMT24 dataset to cover 55 languages by collecting new human-written references and post-edits for 46 new languages and dialects in addition to post-edits of the references in 8 out of 9 languages in the original WMT24 dataset. The dataset covers four domains: literary, news, social, and speech. We benchmark a variety of MT provi"},"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":"2502.12404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T00:39:30Z","cross_cats_sorted":[],"title_canon_sha256":"c040e8f5fc469b5fdfcb7658f47d4580d2327eb8f143fbef034386743441e1e6","abstract_canon_sha256":"b6fcb9bc79c7838ed25c651c37273e5f2ee5f3ca5ac7ebe44a9eb79127074321"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:55.239875Z","signature_b64":"se6pbF7PBwFQewO8IYyvLCMJdbhOUyFVcQw0H4INJDmF7YqlIznUL4bEBByBtuYhgLQ65SHZEyjqyhW1rv9RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf5d8f852fef98631dff9f8245ffcee9ca4b5b2024affd98cc190a628ac9a112","last_reissued_at":"2026-07-05T10:15:55.239470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:55.239470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alison Lui, Biao Zhang, Daniel Deutsch, Eleftheria Briakou, Elizabeth Salesky, Firas Trabelsi, Geza Kovacs, Isaac Caswell, Jason Riesa, Juraj Juraska, Mara Finkelstein, Markus Freitag, Parker Riley, Rebecca Galor, Ricardo Rei, Shruti Rijhwani, Stephanie Winkler","submitted_at":"2025-02-18T00:39:30Z","abstract_excerpt":"As large language models (LLM) become more and more capable in languages other than English, it is important to collect benchmark datasets in order to evaluate their multilingual performance, including on tasks like machine translation (MT). In this work, we extend the WMT24 dataset to cover 55 languages by collecting new human-written references and post-edits for 46 new languages and dialects in addition to post-edits of the references in 8 out of 9 languages in the original WMT24 dataset. The dataset covers four domains: literary, news, social, and speech. We benchmark a variety of MT provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12404","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/2502.12404/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":"2502.12404","created_at":"2026-07-05T10:15:55.239527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12404v1","created_at":"2026-07-05T10:15:55.239527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12404","created_at":"2026-07-05T10:15:55.239527+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5OY7BJP56MG","created_at":"2026-07-05T10:15:55.239527+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5OY7BJP56MGGHP7","created_at":"2026-07-05T10:15:55.239527+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5OY7BJP","created_at":"2026-07-05T10:15:55.239527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28315","citing_title":"HardMTBench: Stress-Testing Chinese-English Translation on Knowledge-Intensive Domains","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22064","citing_title":"Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15229","citing_title":"VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19016","citing_title":"CHORUS: Effort-Aware Multi-Agent Human-AI Collaboration for Professional Translation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12227","citing_title":"A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22520","citing_title":"RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08644","citing_title":"EXAONE 4.5 Technical Report","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5OY7BJP56MGGHP7T6BEL76O5H","json":"https://pith.science/pith/Z5OY7BJP56MGGHP7T6BEL76O5H.json","graph_json":"https://pith.science/api/pith-number/Z5OY7BJP56MGGHP7T6BEL76O5H/graph.json","events_json":"https://pith.science/api/pith-number/Z5OY7BJP56MGGHP7T6BEL76O5H/events.json","paper":"https://pith.science/paper/Z5OY7BJP"},"agent_actions":{"view_html":"https://pith.science/pith/Z5OY7BJP56MGGHP7T6BEL76O5H","download_json":"https://pith.science/pith/Z5OY7BJP56MGGHP7T6BEL76O5H.json","view_paper":"https://pith.science/paper/Z5OY7BJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12404&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5OY7BJP56MGGHP7T6BEL76O5H/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5OY7BJP56MGGHP7T6BEL76O5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5OY7BJP56MGGHP7T6BEL76O5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5OY7BJP56MGGHP7T6BEL76O5H/action/storage_attestation","attest_author":"https://pith.science/pith/Z5OY7BJP56MGGHP7T6BEL76O5H/action/author_attestation","sign_citation":"https://pith.science/pith/Z5OY7BJP56MGGHP7T6BEL76O5H/action/citation_signature","submit_replication":"https://pith.science/pith/Z5OY7BJP56MGGHP7T6BEL76O5H/action/replication_record"}},"created_at":"2026-07-05T10:15:55.239527+00:00","updated_at":"2026-07-05T10:15:55.239527+00:00"}