{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WFTMYACT7ZV3QVQUYJEED56Q4R","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0b3bf49a98abb93dc911010775c01e2b58154c2e82e7858f9d70ae8b798a0d50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T14:09:50Z","title_canon_sha256":"79ac73c993b3bd8de264ec907487345594415b9a0b15b5b27816f59aab71ab3e"},"schema_version":"1.0","source":{"id":"2410.23956","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23956","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23956v2","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23956","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"WFTMYACT7ZV3","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"WFTMYACT7ZV3QVQU","created_at":"2026-07-05T09:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"WFTMYACT","created_at":"2026-07-05T09:31:50Z"}],"graph_snapshots":[{"event_id":"sha256:958a179179ca4b87f2e8e28b198ddc279971dc006f85e5cfbbbb1890349e2809","target":"graph","created_at":"2026-07-05T09:31:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.23956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jiayi Wang, Maurice Weber, Max Ryabinin, Pontus Stenetorp, Raphael Tang, Yao Lu, Yihong Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T14:09:50Z","title":"Multilingual Pretraining Using a Large Corpus Machine-Translated from a Single Source Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23956","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e03e7c16f901a936346b222c6daecb197fc90e74d2f576c2a7f407681288eb3e","target":"record","created_at":"2026-07-05T09:31:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0b3bf49a98abb93dc911010775c01e2b58154c2e82e7858f9d70ae8b798a0d50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T14:09:50Z","title_canon_sha256":"79ac73c993b3bd8de264ec907487345594415b9a0b15b5b27816f59aab71ab3e"},"schema_version":"1.0","source":{"id":"2410.23956","kind":"arxiv","version":2}},"canonical_sha256":"b166cc0053fe6bb85614c24841f7d0e47d899fe958bd09cb4485819ea232b02a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b166cc0053fe6bb85614c24841f7d0e47d899fe958bd09cb4485819ea232b02a","first_computed_at":"2026-07-05T09:31:50.592467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:50.592467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BpducJnnEmqK8TiTIrxTh0xGcl4kycVkw/r1fm5blQRGoYB0WGwZXkzPW0ALdC7Jh22CuU1qdQfFNeW9B8rtBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:50.592914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23956","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e03e7c16f901a936346b222c6daecb197fc90e74d2f576c2a7f407681288eb3e","sha256:958a179179ca4b87f2e8e28b198ddc279971dc006f85e5cfbbbb1890349e2809"],"state_sha256":"96b50822276c868d1b662b1ab3e347cd433fb470fc0b146d3d6c12ba868ff88d"}