{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DMRFVOC2FDAZOC4PBQ3B2HPEZG","short_pith_number":"pith:DMRFVOC2","schema_version":"1.0","canonical_sha256":"1b225ab85a28c1970b8f0c361d1de4c9a2583ec7dd2900ba20a6d30c91e67815","source":{"kind":"arxiv","id":"2405.15032","version":2},"attestation_state":"computed","paper":{"title":"Aya 23: Open Weight Releases to Further Multilingual Progress","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Acyr Locatelli, Ahmet \\\"Ust\\\"un, Aidan Gomez, Bharat Venkitesh, David Cairuz, Dwarak Talupuru, Hangyu Lin, John Dang, Jon Ander Campos, Julia Kreutzer, Kelly Marchisio, Madeline Smith, Marzieh Fadaee, Max Bartolo, Nick Frosst, Phil Blunsom, Sara Hooker, Saurabh Dash, Sebastian Ruder, Viraat Aryabumi, Yi Chern Tan","submitted_at":"2024-05-23T20:10:38Z","abstract_excerpt":"This technical report introduces Aya 23, a family of multilingual language models. Aya 23 builds on the recent release of the Aya model (\\\"Ust\\\"un et al., 2024), focusing on pairing a highly performant pre-trained model with the recently released Aya collection (Singh et al., 2024). The result is a powerful multilingual large language model serving 23 languages, expanding state-of-art language modeling capabilities to approximately half of the world's population. The Aya model covered 101 languages whereas Aya 23 is an experiment in depth vs breadth, exploring the impact of allocating more cap"},"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":"2405.15032","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T20:10:38Z","cross_cats_sorted":[],"title_canon_sha256":"a81b5d1779ce81aa6a3bc147a918b23d1a8b7db25768fc29a1fce5bfd5f7709d","abstract_canon_sha256":"7634d8bfb5563fccf2b412725dcd7e04c94ac7aa9835d66b7c59d314a26ce0e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:34.586132Z","signature_b64":"jNhS9SgZ84zLWDU4S4VoalS42DyD8PThgVeXItnyrqHYRJTFuMOTeJgZpI7Wx4OEa03sFBvmHhb9gkr22yZKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b225ab85a28c1970b8f0c361d1de4c9a2583ec7dd2900ba20a6d30c91e67815","last_reissued_at":"2026-07-05T08:25:34.585610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:34.585610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aya 23: Open Weight Releases to Further Multilingual Progress","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Acyr Locatelli, Ahmet \\\"Ust\\\"un, Aidan Gomez, Bharat Venkitesh, David Cairuz, Dwarak Talupuru, Hangyu Lin, John Dang, Jon Ander Campos, Julia Kreutzer, Kelly Marchisio, Madeline Smith, Marzieh Fadaee, Max Bartolo, Nick Frosst, Phil Blunsom, Sara Hooker, Saurabh Dash, Sebastian Ruder, Viraat Aryabumi, Yi Chern Tan","submitted_at":"2024-05-23T20:10:38Z","abstract_excerpt":"This technical report introduces Aya 23, a family of multilingual language models. Aya 23 builds on the recent release of the Aya model (\\\"Ust\\\"un et al., 2024), focusing on pairing a highly performant pre-trained model with the recently released Aya collection (Singh et al., 2024). The result is a powerful multilingual large language model serving 23 languages, expanding state-of-art language modeling capabilities to approximately half of the world's population. The Aya model covered 101 languages whereas Aya 23 is an experiment in depth vs breadth, exploring the impact of allocating more cap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15032","kind":"arxiv","version":2},"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/2405.15032/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":"2405.15032","created_at":"2026-07-05T08:25:34.585665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15032v2","created_at":"2026-07-05T08:25:34.585665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15032","created_at":"2026-07-05T08:25:34.585665+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMRFVOC2FDAZ","created_at":"2026-07-05T08:25:34.585665+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMRFVOC2FDAZOC4P","created_at":"2026-07-05T08:25:34.585665+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMRFVOC2","created_at":"2026-07-05T08:25:34.585665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24077","citing_title":"Sentence-Level Contextual Entrainment in Large Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17234","citing_title":"Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13218","citing_title":"When Similar Means Different: Evaluating LLMs on Arabic--Hebrew Cognates","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25420","citing_title":"SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22123","citing_title":"Multilingual Vision-Language Models, A Survey","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17001","citing_title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08484","citing_title":"Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16235","citing_title":"Optimizing Korean-Centric LLMs via Token Pruning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMRFVOC2FDAZOC4PBQ3B2HPEZG","json":"https://pith.science/pith/DMRFVOC2FDAZOC4PBQ3B2HPEZG.json","graph_json":"https://pith.science/api/pith-number/DMRFVOC2FDAZOC4PBQ3B2HPEZG/graph.json","events_json":"https://pith.science/api/pith-number/DMRFVOC2FDAZOC4PBQ3B2HPEZG/events.json","paper":"https://pith.science/paper/DMRFVOC2"},"agent_actions":{"view_html":"https://pith.science/pith/DMRFVOC2FDAZOC4PBQ3B2HPEZG","download_json":"https://pith.science/pith/DMRFVOC2FDAZOC4PBQ3B2HPEZG.json","view_paper":"https://pith.science/paper/DMRFVOC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15032&json=true","fetch_graph":"https://pith.science/api/pith-number/DMRFVOC2FDAZOC4PBQ3B2HPEZG/graph.json","fetch_events":"https://pith.science/api/pith-number/DMRFVOC2FDAZOC4PBQ3B2HPEZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMRFVOC2FDAZOC4PBQ3B2HPEZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMRFVOC2FDAZOC4PBQ3B2HPEZG/action/storage_attestation","attest_author":"https://pith.science/pith/DMRFVOC2FDAZOC4PBQ3B2HPEZG/action/author_attestation","sign_citation":"https://pith.science/pith/DMRFVOC2FDAZOC4PBQ3B2HPEZG/action/citation_signature","submit_replication":"https://pith.science/pith/DMRFVOC2FDAZOC4PBQ3B2HPEZG/action/replication_record"}},"created_at":"2026-07-05T08:25:34.585665+00:00","updated_at":"2026-07-05T08:25:34.585665+00:00"}