{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NWGG2EIGAWBIN4T4N27IBJOUZD","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":"4fa1e578089e0d29795f08ca1895fc33c4440a2836262fc8f09b800f980ac377","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T17:34:13Z","title_canon_sha256":"0a60ae4cdfe4a3c65d660227de89047b492775118fcdbee8ea4c855ef32f9337"},"schema_version":"1.0","source":{"id":"2402.07827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07827","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07827v1","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07827","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"NWGG2EIGAWBI","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"pith_short_16","alias_value":"NWGG2EIGAWBIN4T4","created_at":"2026-07-05T07:44:13Z"},{"alias_kind":"pith_short_8","alias_value":"NWGG2EIG","created_at":"2026-07-05T07:44:13Z"}],"graph_snapshots":[{"event_id":"sha256:3c968cd50f35ba465629311ff08718fef156b18db94a2c7cd82b4bd4a9a06c0d","target":"graph","created_at":"2026-07-05T07:44:13Z","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/2402.07827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T17:34:13Z","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07827","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:cb17880304358df0ce709d24de9cacf51fa5c1b370f784c550f8fb6336f49728","target":"record","created_at":"2026-07-05T07:44:13Z","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":"4fa1e578089e0d29795f08ca1895fc33c4440a2836262fc8f09b800f980ac377","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T17:34:13Z","title_canon_sha256":"0a60ae4cdfe4a3c65d660227de89047b492775118fcdbee8ea4c855ef32f9337"},"schema_version":"1.0","source":{"id":"2402.07827","kind":"arxiv","version":1}},"canonical_sha256":"6d8c6d1106058286f27c6ebe80a5d4c8d0e166b4254c76b1df9765eb06ead53c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d8c6d1106058286f27c6ebe80a5d4c8d0e166b4254c76b1df9765eb06ead53c","first_computed_at":"2026-07-05T07:44:13.063333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:13.063333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zHQ5SKfY2VNcF9M52p3RQYzz5IORdIfoRnKi3RA0RTg8wKGVp0qGKaJNiZpJGYvpS8D857fRKgYw1LztQR2dAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:13.063781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb17880304358df0ce709d24de9cacf51fa5c1b370f784c550f8fb6336f49728","sha256:3c968cd50f35ba465629311ff08718fef156b18db94a2c7cd82b4bd4a9a06c0d"],"state_sha256":"c7f35bba74f28e965032c526d7d65afd408abb5adabdb0cb51bd42548cddc3ff"}