{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UZEVBPWSWUXOJBXKOVCLEAKMZV","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":"b44af21142c2853b9955637afd85f235565c08e6d062cef1211ab0e9c7d758fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T11:53:55Z","title_canon_sha256":"51da9ba18b4689272bb8068d633e6dbe7e3d9adbfaf77f23edc8d3860eab7be2"},"schema_version":"1.0","source":{"id":"2503.00865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00865","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00865v1","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00865","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"pith_short_12","alias_value":"UZEVBPWSWUXO","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"pith_short_16","alias_value":"UZEVBPWSWUXOJBXK","created_at":"2026-07-05T10:22:31Z"},{"alias_kind":"pith_short_8","alias_value":"UZEVBPWS","created_at":"2026-07-05T10:22:31Z"}],"graph_snapshots":[{"event_id":"sha256:d5380dfbcf83b8ccd89662a8d599da16b3c5cf2bf6559cb7e2693cbfd1087982","target":"graph","created_at":"2026-07-05T10:22:31Z","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/2503.00865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T11:53:55Z","title":"Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00865","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:ad9e137b18d773710f7d648bf9d54c2f35406a06c8248c71f52364f4ce946214","target":"record","created_at":"2026-07-05T10:22:31Z","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":"b44af21142c2853b9955637afd85f235565c08e6d062cef1211ab0e9c7d758fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T11:53:55Z","title_canon_sha256":"51da9ba18b4689272bb8068d633e6dbe7e3d9adbfaf77f23edc8d3860eab7be2"},"schema_version":"1.0","source":{"id":"2503.00865","kind":"arxiv","version":1}},"canonical_sha256":"a64950bed2b52ee486ea7544b2014ccd75e384fad815c8e1afe246c2d799a691","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a64950bed2b52ee486ea7544b2014ccd75e384fad815c8e1afe246c2d799a691","first_computed_at":"2026-07-05T10:22:31.207006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:31.207006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RToZGHMXywHh58ALwU3Z0BrdH4vDmrt4s3rTx1YLuo2WglcqyMS5enygn+F12q3mLFTycM1YWgM4yfomKBkoDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:31.207511Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad9e137b18d773710f7d648bf9d54c2f35406a06c8248c71f52364f4ce946214","sha256:d5380dfbcf83b8ccd89662a8d599da16b3c5cf2bf6559cb7e2693cbfd1087982"],"state_sha256":"5b4078097dd0c87cfa370c709e68b42ad1a425b6136fb01f8fa1e550d0f0b881"}