{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DIS4KF3BWMWWKJJSYA2SRQYMVD","short_pith_number":"pith:DIS4KF3B","schema_version":"1.0","canonical_sha256":"1a25c51761b32d652532c03528c30ca8d5b7d35d4269a03b9b5f3d2139e45c40","source":{"kind":"arxiv","id":"2502.04314","version":2},"attestation_state":"computed","paper":{"title":"BOUQuET: dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Ventayol-Boada, Alex Mourachko, Arina Turkatenko, Christophe Ropers, Cynthia Gao, David Dale, Eduardo S\\'anchez, Ioannis Tsiamas, Jean Maillard, Joe Chuang, Mariano Coria Meglioli, Marta R. Costa-juss\\`a, Mikel Artetxe, Pierre Andrews, Safiyyah Saleem, Shireen Yates, The Omnilingual MT Team","submitted_at":"2025-02-06T18:56:37Z","abstract_excerpt":"BOUQuET is a multi-way, multicentric and multi-register/domain dataset and benchmark, and a broader collaborative initiative. This dataset is handcrafted in 8 non-English languages. Each of these source languages are representative of the most widely spoken ones and therefore they have the potential to serve as pivot languages that will enable more accurate translations. The dataset is multicentric to enforce representation of multilingual language features. In addition, the dataset goes beyond the sentence level, as it is organized in paragraphs of various lengths. Compared with related machi"},"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":"2502.04314","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T18:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"51e0c6a1947b529200dc8fd947723b7865be81f4dc2906f763435dc77005d988","abstract_canon_sha256":"d758e0139ec737f2781cc4cd40393866d658fb2298006bcc93fb5ca6c7567f12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:15.096842Z","signature_b64":"0uTDaOgDfBS+YX/F0N6YNQroiZYS2IbGQV5U+Jwquegva3TWbYfg+apM6yhFdQZp74f6uA83567Gu0I4IPb1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a25c51761b32d652532c03528c30ca8d5b7d35d4269a03b9b5f3d2139e45c40","last_reissued_at":"2026-07-05T11:21:15.096334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:15.096334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BOUQuET: dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Ventayol-Boada, Alex Mourachko, Arina Turkatenko, Christophe Ropers, Cynthia Gao, David Dale, Eduardo S\\'anchez, Ioannis Tsiamas, Jean Maillard, Joe Chuang, Mariano Coria Meglioli, Marta R. Costa-juss\\`a, Mikel Artetxe, Pierre Andrews, Safiyyah Saleem, Shireen Yates, The Omnilingual MT Team","submitted_at":"2025-02-06T18:56:37Z","abstract_excerpt":"BOUQuET is a multi-way, multicentric and multi-register/domain dataset and benchmark, and a broader collaborative initiative. This dataset is handcrafted in 8 non-English languages. Each of these source languages are representative of the most widely spoken ones and therefore they have the potential to serve as pivot languages that will enable more accurate translations. The dataset is multicentric to enforce representation of multilingual language features. In addition, the dataset goes beyond the sentence level, as it is organized in paragraphs of various lengths. Compared with related machi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04314","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/2502.04314/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":"2502.04314","created_at":"2026-07-05T11:21:15.096398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04314v2","created_at":"2026-07-05T11:21:15.096398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04314","created_at":"2026-07-05T11:21:15.096398+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIS4KF3BWMWW","created_at":"2026-07-05T11:21:15.096398+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIS4KF3BWMWWKJJS","created_at":"2026-07-05T11:21:15.096398+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIS4KF3B","created_at":"2026-07-05T11:21:15.096398+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/DIS4KF3BWMWWKJJSYA2SRQYMVD","json":"https://pith.science/pith/DIS4KF3BWMWWKJJSYA2SRQYMVD.json","graph_json":"https://pith.science/api/pith-number/DIS4KF3BWMWWKJJSYA2SRQYMVD/graph.json","events_json":"https://pith.science/api/pith-number/DIS4KF3BWMWWKJJSYA2SRQYMVD/events.json","paper":"https://pith.science/paper/DIS4KF3B"},"agent_actions":{"view_html":"https://pith.science/pith/DIS4KF3BWMWWKJJSYA2SRQYMVD","download_json":"https://pith.science/pith/DIS4KF3BWMWWKJJSYA2SRQYMVD.json","view_paper":"https://pith.science/paper/DIS4KF3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04314&json=true","fetch_graph":"https://pith.science/api/pith-number/DIS4KF3BWMWWKJJSYA2SRQYMVD/graph.json","fetch_events":"https://pith.science/api/pith-number/DIS4KF3BWMWWKJJSYA2SRQYMVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIS4KF3BWMWWKJJSYA2SRQYMVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIS4KF3BWMWWKJJSYA2SRQYMVD/action/storage_attestation","attest_author":"https://pith.science/pith/DIS4KF3BWMWWKJJSYA2SRQYMVD/action/author_attestation","sign_citation":"https://pith.science/pith/DIS4KF3BWMWWKJJSYA2SRQYMVD/action/citation_signature","submit_replication":"https://pith.science/pith/DIS4KF3BWMWWKJJSYA2SRQYMVD/action/replication_record"}},"created_at":"2026-07-05T11:21:15.096398+00:00","updated_at":"2026-07-05T11:21:15.096398+00:00"}