{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D6PJFZBXTR3XMI5BDXAYKF7TWR","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":"fc60a8470c2e7061ff144505e383498402bb669c7a5c06387bb443cad9cf8a38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T19:27:53Z","title_canon_sha256":"6b30526d060783a946f0cdae52395e08d03b159cdcca761c105ab1e9e26e424a"},"schema_version":"1.0","source":{"id":"2502.13252","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13252","created_at":"2026-07-05T10:16:44Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13252v1","created_at":"2026-07-05T10:16:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13252","created_at":"2026-07-05T10:16:44Z"},{"alias_kind":"pith_short_12","alias_value":"D6PJFZBXTR3X","created_at":"2026-07-05T10:16:44Z"},{"alias_kind":"pith_short_16","alias_value":"D6PJFZBXTR3XMI5B","created_at":"2026-07-05T10:16:44Z"},{"alias_kind":"pith_short_8","alias_value":"D6PJFZBX","created_at":"2026-07-05T10:16:44Z"}],"graph_snapshots":[{"event_id":"sha256:5f88e492e0243960245fa82b0f87ceba662d1877261e982fbf34c1c67231ae5f","target":"graph","created_at":"2026-07-05T10:16:44Z","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/2502.13252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-resource languages such as English, enables the pretraining of high-quality large language models (LLMs). The same can not be said for most other languages as 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 texts from a single high-quality source language can contribute significantly to the pretraining quality of multilingual LLMs. We translate FineWeb-Edu, a high-quality English web dataset, into nine languages, resulting in a 1.7-trillion-t","authors_text":"David Adelani, 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":"2025-02-18T19:27:53Z","title":"Multilingual Language Model Pretraining using Machine-translated Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13252","kind":"arxiv","version":1},"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:dbce28eb7a785ee5b534f4221361450ab4dfb577bea94792b8a111b313ac5e25","target":"record","created_at":"2026-07-05T10:16:44Z","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":"fc60a8470c2e7061ff144505e383498402bb669c7a5c06387bb443cad9cf8a38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T19:27:53Z","title_canon_sha256":"6b30526d060783a946f0cdae52395e08d03b159cdcca761c105ab1e9e26e424a"},"schema_version":"1.0","source":{"id":"2502.13252","kind":"arxiv","version":1}},"canonical_sha256":"1f9e92e4379c777623a11dc18517f3b46b11b7468ebf2e0b7774b82be5c4096f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f9e92e4379c777623a11dc18517f3b46b11b7468ebf2e0b7774b82be5c4096f","first_computed_at":"2026-07-05T10:16:44.387123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:44.387123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R3GQZgAG6B/43mLVOer6w9NSNG33/pDQr2cyknN7oZhldG+NYc93QJNmr7SUyUxyR+RJ1chDlgNQ9T1kdMgUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:44.387595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13252","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbce28eb7a785ee5b534f4221361450ab4dfb577bea94792b8a111b313ac5e25","sha256:5f88e492e0243960245fa82b0f87ceba662d1877261e982fbf34c1c67231ae5f"],"state_sha256":"4a7afce1c1be7baee827aa034fe91d5fe7373720bef9256da21d4fa346e2229f"}