{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2RY2OQYDZ325VZTKCV4ANXYWYY","short_pith_number":"pith:2RY2OQYD","schema_version":"1.0","canonical_sha256":"d471a74303cef5dae66a157806df16c6239d7aea1bc901af71d9ba6026fd587f","source":{"kind":"arxiv","id":"2408.06273","version":3},"attestation_state":"computed","paper":{"title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Haoran Sun, Jiangcun Du, Juesi Xiao, Lei Yang, Leiyu Pan, Ling Shi, Menglong Cui, Renren Jin, Shaolin Zhu, Shaoyang Xu, Supryadi, Yikun Lei","submitted_at":"2024-08-12T16:34:56Z","abstract_excerpt":"Large language models (LLMs) have demonstrated prowess in a wide range of tasks. However, many LLMs exhibit significant performance discrepancies between high- and low-resource languages. To mitigate this challenge, we present FuxiTranyu, an open-source multilingual LLM, which is designed to satisfy the need of the research community for balanced and high-performing multilingual capabilities. The base model, FuxiTranyu-8B, features 8 billion parameters and is trained from scratch on meticulously balanced multilingual data that contains 600 billion tokens covering 43 natural languages and 16 pr"},"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":"2408.06273","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T16:34:56Z","cross_cats_sorted":[],"title_canon_sha256":"b968a74aca1cce99382d96eeb8135e4eac1280dd2ecf52e808aa03e9b6c58500","abstract_canon_sha256":"175b64b739d628b81856fc32b95edd53b12e0564e2d0f5a5a2b370e5e09bf10b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:29.891594Z","signature_b64":"NIS8olTnUPosdlqAF3Aq9n8Ao03Wd9Syd9cZ3+GwZygDKWh+4qRafo5EiJLe4Ccr8yxvE7x1OdwPcAEE9WlcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d471a74303cef5dae66a157806df16c6239d7aea1bc901af71d9ba6026fd587f","last_reissued_at":"2026-07-05T09:26:29.891071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:29.891071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Haoran Sun, Jiangcun Du, Juesi Xiao, Lei Yang, Leiyu Pan, Ling Shi, Menglong Cui, Renren Jin, Shaolin Zhu, Shaoyang Xu, Supryadi, Yikun Lei","submitted_at":"2024-08-12T16:34:56Z","abstract_excerpt":"Large language models (LLMs) have demonstrated prowess in a wide range of tasks. However, many LLMs exhibit significant performance discrepancies between high- and low-resource languages. To mitigate this challenge, we present FuxiTranyu, an open-source multilingual LLM, which is designed to satisfy the need of the research community for balanced and high-performing multilingual capabilities. The base model, FuxiTranyu-8B, features 8 billion parameters and is trained from scratch on meticulously balanced multilingual data that contains 600 billion tokens covering 43 natural languages and 16 pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06273","kind":"arxiv","version":3},"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/2408.06273/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":"2408.06273","created_at":"2026-07-05T09:26:29.891131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06273v3","created_at":"2026-07-05T09:26:29.891131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06273","created_at":"2026-07-05T09:26:29.891131+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RY2OQYDZ325","created_at":"2026-07-05T09:26:29.891131+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RY2OQYDZ325VZTK","created_at":"2026-07-05T09:26:29.891131+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RY2OQYD","created_at":"2026-07-05T09:26:29.891131+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14256","citing_title":"FuxiMT: Sparsifying Large Language Models for Chinese-Centric Multilingual Machine Translation","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RY2OQYDZ325VZTKCV4ANXYWYY","json":"https://pith.science/pith/2RY2OQYDZ325VZTKCV4ANXYWYY.json","graph_json":"https://pith.science/api/pith-number/2RY2OQYDZ325VZTKCV4ANXYWYY/graph.json","events_json":"https://pith.science/api/pith-number/2RY2OQYDZ325VZTKCV4ANXYWYY/events.json","paper":"https://pith.science/paper/2RY2OQYD"},"agent_actions":{"view_html":"https://pith.science/pith/2RY2OQYDZ325VZTKCV4ANXYWYY","download_json":"https://pith.science/pith/2RY2OQYDZ325VZTKCV4ANXYWYY.json","view_paper":"https://pith.science/paper/2RY2OQYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06273&json=true","fetch_graph":"https://pith.science/api/pith-number/2RY2OQYDZ325VZTKCV4ANXYWYY/graph.json","fetch_events":"https://pith.science/api/pith-number/2RY2OQYDZ325VZTKCV4ANXYWYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RY2OQYDZ325VZTKCV4ANXYWYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RY2OQYDZ325VZTKCV4ANXYWYY/action/storage_attestation","attest_author":"https://pith.science/pith/2RY2OQYDZ325VZTKCV4ANXYWYY/action/author_attestation","sign_citation":"https://pith.science/pith/2RY2OQYDZ325VZTKCV4ANXYWYY/action/citation_signature","submit_replication":"https://pith.science/pith/2RY2OQYDZ325VZTKCV4ANXYWYY/action/replication_record"}},"created_at":"2026-07-05T09:26:29.891131+00:00","updated_at":"2026-07-05T09:26:29.891131+00:00"}