{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UZEVBPWSWUXOJBXKOVCLEAKMZV","short_pith_number":"pith:UZEVBPWS","schema_version":"1.0","canonical_sha256":"a64950bed2b52ee486ea7544b2014ccd75e384fad815c8e1afe246c2d799a691","source":{"kind":"arxiv","id":"2503.00865","version":1},"attestation_state":"computed","paper":{"title":"Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chaoqun Liu, Deli Zhao, Hou Pong Chan, Jiahao Ying, Lidong Bing, Mahani Aljunied, Wenxuan Zhang, Yiran Zhao, Yue Deng, Yu Rong, Zhaodonghui Li","submitted_at":"2025-03-02T11:53:55Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing (NLP), yet open-source multilingual LLMs remain scarce, with existing models often limited in language coverage. Such models typically prioritize well-resourced languages, while widely spoken but under-resourced languages are often overlooked. To address this disparity, we introduce $\\texttt{Babel}$, an open multilingual LLM that covers the top 25 languages by number of speakers, supports over 90% of the global population, and includes many languages neglected by other open multilingual LLMs. Unlike traditional contin"},"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":"2503.00865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T11:53:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"51da9ba18b4689272bb8068d633e6dbe7e3d9adbfaf77f23edc8d3860eab7be2","abstract_canon_sha256":"b44af21142c2853b9955637afd85f235565c08e6d062cef1211ab0e9c7d758fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:31.207511Z","signature_b64":"RToZGHMXywHh58ALwU3Z0BrdH4vDmrt4s3rTx1YLuo2WglcqyMS5enygn+F12q3mLFTycM1YWgM4yfomKBkoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a64950bed2b52ee486ea7544b2014ccd75e384fad815c8e1afe246c2d799a691","last_reissued_at":"2026-07-05T10:22:31.207006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:31.207006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chaoqun Liu, Deli Zhao, Hou Pong Chan, Jiahao Ying, Lidong Bing, Mahani Aljunied, Wenxuan Zhang, Yiran Zhao, Yue Deng, Yu Rong, Zhaodonghui Li","submitted_at":"2025-03-02T11:53:55Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing (NLP), yet open-source multilingual LLMs remain scarce, with existing models often limited in language coverage. Such models typically prioritize well-resourced languages, while widely spoken but under-resourced languages are often overlooked. To address this disparity, we introduce $\\texttt{Babel}$, an open multilingual LLM that covers the top 25 languages by number of speakers, supports over 90% of the global population, and includes many languages neglected by other open multilingual LLMs. Unlike traditional contin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00865","kind":"arxiv","version":1},"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/2503.00865/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":"2503.00865","created_at":"2026-07-05T10:22:31.207068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00865v1","created_at":"2026-07-05T10:22:31.207068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00865","created_at":"2026-07-05T10:22:31.207068+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZEVBPWSWUXO","created_at":"2026-07-05T10:22:31.207068+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZEVBPWSWUXOJBXK","created_at":"2026-07-05T10:22:31.207068+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZEVBPWS","created_at":"2026-07-05T10:22:31.207068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.18788","citing_title":"BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZEVBPWSWUXOJBXKOVCLEAKMZV","json":"https://pith.science/pith/UZEVBPWSWUXOJBXKOVCLEAKMZV.json","graph_json":"https://pith.science/api/pith-number/UZEVBPWSWUXOJBXKOVCLEAKMZV/graph.json","events_json":"https://pith.science/api/pith-number/UZEVBPWSWUXOJBXKOVCLEAKMZV/events.json","paper":"https://pith.science/paper/UZEVBPWS"},"agent_actions":{"view_html":"https://pith.science/pith/UZEVBPWSWUXOJBXKOVCLEAKMZV","download_json":"https://pith.science/pith/UZEVBPWSWUXOJBXKOVCLEAKMZV.json","view_paper":"https://pith.science/paper/UZEVBPWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00865&json=true","fetch_graph":"https://pith.science/api/pith-number/UZEVBPWSWUXOJBXKOVCLEAKMZV/graph.json","fetch_events":"https://pith.science/api/pith-number/UZEVBPWSWUXOJBXKOVCLEAKMZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZEVBPWSWUXOJBXKOVCLEAKMZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZEVBPWSWUXOJBXKOVCLEAKMZV/action/storage_attestation","attest_author":"https://pith.science/pith/UZEVBPWSWUXOJBXKOVCLEAKMZV/action/author_attestation","sign_citation":"https://pith.science/pith/UZEVBPWSWUXOJBXKOVCLEAKMZV/action/citation_signature","submit_replication":"https://pith.science/pith/UZEVBPWSWUXOJBXKOVCLEAKMZV/action/replication_record"}},"created_at":"2026-07-05T10:22:31.207068+00:00","updated_at":"2026-07-05T10:22:31.207068+00:00"}