{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WFTMYACT7ZV3QVQUYJEED56Q4R","short_pith_number":"pith:WFTMYACT","schema_version":"1.0","canonical_sha256":"b166cc0053fe6bb85614c24841f7d0e47d899fe958bd09cb4485819ea232b02a","source":{"kind":"arxiv","id":"2410.23956","version":2},"attestation_state":"computed","paper":{"title":"Multilingual Pretraining Using a Large Corpus Machine-Translated from a Single Source Language","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiayi Wang, Maurice Weber, Max Ryabinin, Pontus Stenetorp, Raphael Tang, Yao Lu, Yihong Chen","submitted_at":"2024-10-31T14:09:50Z","abstract_excerpt":"English, as a very high-resource language, enables the pretraining of high-quality large language models (LLMs). The same cannot be said for most other languages, as leading LLMs still underperform for non-English languages, likely due to a gap in the quality and diversity of the available multilingual pretraining corpora. In this work, we find that machine-translated text from a single high-quality source language can contribute significantly to the pretraining of multilingual LLMs. We translate FineWeb-Edu, a high-quality English web dataset, into French, German, and Spanish, resulting in a "},"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":"2410.23956","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T14:09:50Z","cross_cats_sorted":[],"title_canon_sha256":"79ac73c993b3bd8de264ec907487345594415b9a0b15b5b27816f59aab71ab3e","abstract_canon_sha256":"0b3bf49a98abb93dc911010775c01e2b58154c2e82e7858f9d70ae8b798a0d50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:50.592914Z","signature_b64":"BpducJnnEmqK8TiTIrxTh0xGcl4kycVkw/r1fm5blQRGoYB0WGwZXkzPW0ALdC7Jh22CuU1qdQfFNeW9B8rtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b166cc0053fe6bb85614c24841f7d0e47d899fe958bd09cb4485819ea232b02a","last_reissued_at":"2026-07-05T09:31:50.592467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:50.592467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Pretraining Using a Large Corpus Machine-Translated from a Single Source Language","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiayi Wang, Maurice Weber, Max Ryabinin, Pontus Stenetorp, Raphael Tang, Yao Lu, Yihong Chen","submitted_at":"2024-10-31T14:09:50Z","abstract_excerpt":"English, as a very high-resource language, enables the pretraining of high-quality large language models (LLMs). The same cannot be said for most other languages, as leading LLMs still underperform for non-English languages, likely due to a gap in the quality and diversity of the available multilingual pretraining corpora. In this work, we find that machine-translated text from a single high-quality source language can contribute significantly to the pretraining of multilingual LLMs. We translate FineWeb-Edu, a high-quality English web dataset, into French, German, and Spanish, resulting in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23956","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/2410.23956/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":"2410.23956","created_at":"2026-07-05T09:31:50.592531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23956v2","created_at":"2026-07-05T09:31:50.592531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23956","created_at":"2026-07-05T09:31:50.592531+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFTMYACT7ZV3","created_at":"2026-07-05T09:31:50.592531+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFTMYACT7ZV3QVQU","created_at":"2026-07-05T09:31:50.592531+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFTMYACT","created_at":"2026-07-05T09:31:50.592531+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/WFTMYACT7ZV3QVQUYJEED56Q4R","json":"https://pith.science/pith/WFTMYACT7ZV3QVQUYJEED56Q4R.json","graph_json":"https://pith.science/api/pith-number/WFTMYACT7ZV3QVQUYJEED56Q4R/graph.json","events_json":"https://pith.science/api/pith-number/WFTMYACT7ZV3QVQUYJEED56Q4R/events.json","paper":"https://pith.science/paper/WFTMYACT"},"agent_actions":{"view_html":"https://pith.science/pith/WFTMYACT7ZV3QVQUYJEED56Q4R","download_json":"https://pith.science/pith/WFTMYACT7ZV3QVQUYJEED56Q4R.json","view_paper":"https://pith.science/paper/WFTMYACT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23956&json=true","fetch_graph":"https://pith.science/api/pith-number/WFTMYACT7ZV3QVQUYJEED56Q4R/graph.json","fetch_events":"https://pith.science/api/pith-number/WFTMYACT7ZV3QVQUYJEED56Q4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFTMYACT7ZV3QVQUYJEED56Q4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFTMYACT7ZV3QVQUYJEED56Q4R/action/storage_attestation","attest_author":"https://pith.science/pith/WFTMYACT7ZV3QVQUYJEED56Q4R/action/author_attestation","sign_citation":"https://pith.science/pith/WFTMYACT7ZV3QVQUYJEED56Q4R/action/citation_signature","submit_replication":"https://pith.science/pith/WFTMYACT7ZV3QVQUYJEED56Q4R/action/replication_record"}},"created_at":"2026-07-05T09:31:50.592531+00:00","updated_at":"2026-07-05T09:31:50.592531+00:00"}