{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EZVJXSXUDS4DF7TUA7Q6YUPLN4","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":"b49f2392231774d20221bb823440de9a4321438cbbf7f38b8466dfb747d159df","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T17:03:48Z","title_canon_sha256":"23142bfbbba96e13e2c41c4876c8b3da74b6c5264af760ec3f42bd5c3de6a8f7"},"schema_version":"1.0","source":{"id":"2505.08751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08751","created_at":"2026-07-05T11:02:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08751v1","created_at":"2026-07-05T11:02:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08751","created_at":"2026-07-05T11:02:36Z"},{"alias_kind":"pith_short_12","alias_value":"EZVJXSXUDS4D","created_at":"2026-07-05T11:02:36Z"},{"alias_kind":"pith_short_16","alias_value":"EZVJXSXUDS4DF7TU","created_at":"2026-07-05T11:02:36Z"},{"alias_kind":"pith_short_8","alias_value":"EZVJXSXU","created_at":"2026-07-05T11:02:36Z"}],"graph_snapshots":[{"event_id":"sha256:9e449e7d06cd2b4b188baa612faaa90d88ed22d50a74f81f9198965dc7e09583","target":"graph","created_at":"2026-07-05T11:02:36Z","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/2505.08751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building multimodal language models is fundamentally challenging: it requires aligning vision and language modalities, curating high-quality instruction data, and avoiding the degradation of existing text-only capabilities once vision is introduced. These difficulties are further magnified in the multilingual setting, where the need for multimodal data in different languages exacerbates existing data scarcity, machine translation often distorts meaning, and catastrophic forgetting is more pronounced. To address the aforementioned challenges, we introduce novel techniques spanning both data and","authors_text":"Acyr Locatelli, Ahmet \\\"Ust\\\"un, Aidan Gomez, Arash Ahmadian, Beyza Ermis, Bharat Venkitesh, Ivan Zhang, Jason Ozuzu, Jeremy Pekmez, John Dang, Madeline Smith, Manoj Govindassamy, Marzieh Fadaee, Matthias Gall\\'e, Nick Frosst, Phil Blunsom, Pierre Richemond, Sara Hooker, Saurabh Dash, Shivalika Singh, Sudip Roy, Viraat Aryabumi, Vlad Shmyhlo, Walter Beller-Morales, Yiyang Nan","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T17:03:48Z","title":"Aya Vision: Advancing the Frontier of Multilingual Multimodality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08751","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:d29c8062cf53ccbf3ef12db35b8b7af68f896d1d496128401a1d4bca3ddb9a4e","target":"record","created_at":"2026-07-05T11:02:36Z","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":"b49f2392231774d20221bb823440de9a4321438cbbf7f38b8466dfb747d159df","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T17:03:48Z","title_canon_sha256":"23142bfbbba96e13e2c41c4876c8b3da74b6c5264af760ec3f42bd5c3de6a8f7"},"schema_version":"1.0","source":{"id":"2505.08751","kind":"arxiv","version":1}},"canonical_sha256":"266a9bcaf41cb832fe7407e1ec51eb6f31be5dcbfeb78a128b0cf721777ee9c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"266a9bcaf41cb832fe7407e1ec51eb6f31be5dcbfeb78a128b0cf721777ee9c1","first_computed_at":"2026-07-05T11:02:36.001505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:36.001505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m2TFQckkppQ6zViR+D4ibqMWQ2/lKxh73wiSwFThU9bjdykqK8VWwHhl+vYiQuukvk6/8piXWsnmM9ztFkQJBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:36.001991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d29c8062cf53ccbf3ef12db35b8b7af68f896d1d496128401a1d4bca3ddb9a4e","sha256:9e449e7d06cd2b4b188baa612faaa90d88ed22d50a74f81f9198965dc7e09583"],"state_sha256":"d19bbd46cffde6e52d80ef9244209f84e1ac8fbaedd86842d5d72759910f1232"}