{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NWGG2EIGAWBIN4T4N27IBJOUZD","short_pith_number":"pith:NWGG2EIG","schema_version":"1.0","canonical_sha256":"6d8c6d1106058286f27c6ebe80a5d4c8d0e166b4254c76b1df9765eb06ead53c","source":{"kind":"arxiv","id":"2402.07827","version":1},"attestation_state":"computed","paper":{"title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmet \\\"Ust\\\"un, Amr Kayid, Daniel D'souza, Freddie Vargus, Gbemileke Onilude, Hui-Lee Ooi, Julia Kreutzer, Marzieh Fadaee, Neel Bhandari, Niklas Muennighoff, Phil Blunsom, Sara Hooker, Shayne Longpre, Shivalika Singh, Viraat Aryabumi, Wei-Yin Ko, Zheng-Xin Yong","submitted_at":"2024-02-12T17:34:13Z","abstract_excerpt":"Recent breakthroughs in large language models (LLMs) have centered around a handful of data-rich languages. What does it take to broaden access to breakthroughs beyond first-class citizen languages? Our work introduces Aya, a massively multilingual generative language model that follows instructions in 101 languages of which over 50% are considered as lower-resourced. Aya outperforms mT0 and BLOOMZ on the majority of tasks while covering double the number of languages. We introduce extensive new evaluation suites that broaden the state-of-art for multilingual eval across 99 languages -- includ"},"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":"2402.07827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T17:34:13Z","cross_cats_sorted":[],"title_canon_sha256":"0a60ae4cdfe4a3c65d660227de89047b492775118fcdbee8ea4c855ef32f9337","abstract_canon_sha256":"4fa1e578089e0d29795f08ca1895fc33c4440a2836262fc8f09b800f980ac377"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:13.063781Z","signature_b64":"zHQ5SKfY2VNcF9M52p3RQYzz5IORdIfoRnKi3RA0RTg8wKGVp0qGKaJNiZpJGYvpS8D857fRKgYw1LztQR2dAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d8c6d1106058286f27c6ebe80a5d4c8d0e166b4254c76b1df9765eb06ead53c","last_reissued_at":"2026-07-05T07:44:13.063333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:13.063333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmet \\\"Ust\\\"un, Amr Kayid, Daniel D'souza, Freddie Vargus, Gbemileke Onilude, Hui-Lee Ooi, Julia Kreutzer, Marzieh Fadaee, Neel Bhandari, Niklas Muennighoff, Phil Blunsom, Sara Hooker, Shayne Longpre, Shivalika Singh, Viraat Aryabumi, Wei-Yin Ko, Zheng-Xin Yong","submitted_at":"2024-02-12T17:34:13Z","abstract_excerpt":"Recent breakthroughs in large language models (LLMs) have centered around a handful of data-rich languages. What does it take to broaden access to breakthroughs beyond first-class citizen languages? Our work introduces Aya, a massively multilingual generative language model that follows instructions in 101 languages of which over 50% are considered as lower-resourced. Aya outperforms mT0 and BLOOMZ on the majority of tasks while covering double the number of languages. We introduce extensive new evaluation suites that broaden the state-of-art for multilingual eval across 99 languages -- includ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07827","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/2402.07827/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":"2402.07827","created_at":"2026-07-05T07:44:13.063394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07827v1","created_at":"2026-07-05T07:44:13.063394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07827","created_at":"2026-07-05T07:44:13.063394+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWGG2EIGAWBI","created_at":"2026-07-05T07:44:13.063394+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWGG2EIGAWBIN4T4","created_at":"2026-07-05T07:44:13.063394+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWGG2EIG","created_at":"2026-07-05T07:44:13.063394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06738","citing_title":"Modular Monolingual Adaptation using Pretrained Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07874","citing_title":"Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2406.11794","citing_title":"DataComp-LM: In search of the next generation of training sets for language models","ref_index":188,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11255","citing_title":"HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19173","citing_title":"StarCoder 2 and The Stack v2: The Next Generation","ref_index":290,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02601","citing_title":"SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19678","citing_title":"Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWGG2EIGAWBIN4T4N27IBJOUZD","json":"https://pith.science/pith/NWGG2EIGAWBIN4T4N27IBJOUZD.json","graph_json":"https://pith.science/api/pith-number/NWGG2EIGAWBIN4T4N27IBJOUZD/graph.json","events_json":"https://pith.science/api/pith-number/NWGG2EIGAWBIN4T4N27IBJOUZD/events.json","paper":"https://pith.science/paper/NWGG2EIG"},"agent_actions":{"view_html":"https://pith.science/pith/NWGG2EIGAWBIN4T4N27IBJOUZD","download_json":"https://pith.science/pith/NWGG2EIGAWBIN4T4N27IBJOUZD.json","view_paper":"https://pith.science/paper/NWGG2EIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07827&json=true","fetch_graph":"https://pith.science/api/pith-number/NWGG2EIGAWBIN4T4N27IBJOUZD/graph.json","fetch_events":"https://pith.science/api/pith-number/NWGG2EIGAWBIN4T4N27IBJOUZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWGG2EIGAWBIN4T4N27IBJOUZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWGG2EIGAWBIN4T4N27IBJOUZD/action/storage_attestation","attest_author":"https://pith.science/pith/NWGG2EIGAWBIN4T4N27IBJOUZD/action/author_attestation","sign_citation":"https://pith.science/pith/NWGG2EIGAWBIN4T4N27IBJOUZD/action/citation_signature","submit_replication":"https://pith.science/pith/NWGG2EIGAWBIN4T4N27IBJOUZD/action/replication_record"}},"created_at":"2026-07-05T07:44:13.063394+00:00","updated_at":"2026-07-05T07:44:13.063394+00:00"}