{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2RY2OQYDZ325VZTKCV4ANXYWYY","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":"175b64b739d628b81856fc32b95edd53b12e0564e2d0f5a5a2b370e5e09bf10b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T16:34:56Z","title_canon_sha256":"b968a74aca1cce99382d96eeb8135e4eac1280dd2ecf52e808aa03e9b6c58500"},"schema_version":"1.0","source":{"id":"2408.06273","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06273","created_at":"2026-07-05T09:26:29Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06273v3","created_at":"2026-07-05T09:26:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06273","created_at":"2026-07-05T09:26:29Z"},{"alias_kind":"pith_short_12","alias_value":"2RY2OQYDZ325","created_at":"2026-07-05T09:26:29Z"},{"alias_kind":"pith_short_16","alias_value":"2RY2OQYDZ325VZTK","created_at":"2026-07-05T09:26:29Z"},{"alias_kind":"pith_short_8","alias_value":"2RY2OQYD","created_at":"2026-07-05T09:26:29Z"}],"graph_snapshots":[{"event_id":"sha256:04574917920eda93cf5aa37c2b81ff179313667d1ba77861d8bd319bf709cf34","target":"graph","created_at":"2026-07-05T09:26:29Z","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/2408.06273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T16:34:56Z","title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06273","kind":"arxiv","version":3},"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":"sha256:5d5e05d4822e90dbe01b6e998a6d017f94ed5b3d3b7293b6430279c8b728d3fb","target":"record","created_at":"2026-07-05T09:26:29Z","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":"175b64b739d628b81856fc32b95edd53b12e0564e2d0f5a5a2b370e5e09bf10b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T16:34:56Z","title_canon_sha256":"b968a74aca1cce99382d96eeb8135e4eac1280dd2ecf52e808aa03e9b6c58500"},"schema_version":"1.0","source":{"id":"2408.06273","kind":"arxiv","version":3}},"canonical_sha256":"d471a74303cef5dae66a157806df16c6239d7aea1bc901af71d9ba6026fd587f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d471a74303cef5dae66a157806df16c6239d7aea1bc901af71d9ba6026fd587f","first_computed_at":"2026-07-05T09:26:29.891071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:29.891071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NIS8olTnUPosdlqAF3Aq9n8Ao03Wd9Syd9cZ3+GwZygDKWh+4qRafo5EiJLe4Ccr8yxvE7x1OdwPcAEE9WlcBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:29.891594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06273","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d5e05d4822e90dbe01b6e998a6d017f94ed5b3d3b7293b6430279c8b728d3fb","sha256:04574917920eda93cf5aa37c2b81ff179313667d1ba77861d8bd319bf709cf34"],"state_sha256":"d3783afda53a7d07820c35759141b15f29e99acdb51a7167db19beec1ec92f9a"}