{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JRWYOJOS3OIKARBPTOJFIWAGEM","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":"1dfe66db0d1ae29669f6ad49c619f1854c2a27cb397da0f659d2b7057f8f6fba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T14:47:35Z","title_canon_sha256":"9a6b01c0febc0c8d8896355c97f598fe9829532e6bca84692f86a57cd7d2e3b5"},"schema_version":"1.0","source":{"id":"2603.16606","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16606","created_at":"2026-06-19T16:12:53Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16606v3","created_at":"2026-06-19T16:12:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16606","created_at":"2026-06-19T16:12:53Z"},{"alias_kind":"pith_short_12","alias_value":"JRWYOJOS3OIK","created_at":"2026-06-19T16:12:53Z"},{"alias_kind":"pith_short_16","alias_value":"JRWYOJOS3OIKARBP","created_at":"2026-06-19T16:12:53Z"},{"alias_kind":"pith_short_8","alias_value":"JRWYOJOS","created_at":"2026-06-19T16:12:53Z"}],"graph_snapshots":[{"event_id":"sha256:8db628492ce862f57d4e90afffc9593b936ee700077a368f945a297eb675fc36","target":"graph","created_at":"2026-06-19T16:12:53Z","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/2603.16606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual sentence encoders typically cover only a few hundred languages and often trade downstream quality for stronger alignment, limiting their adoption. We introduce OmniSONAR, a new family of omnilingual, cross-lingual and cross-modal sentence embedding models that natively embed text, speech, code, and mathematical expressions in a single semantic space, while delivering state-of-the-art downstream performance at the scale of thousands of languages, from high-resource to extremely low-resource varieties. To reach this scale without representation collapse, we use progressive training","authors_text":"Alexandre Mourachko, Artyom Kozhevnikov, Belen Alastruey, Christophe Ropers, David Dale, Guillem Ram\\'irez, Holger Schwenk, Ioannis Tsiamas, Jaehyeong Jo, Kevin Heffernan, Loic Barrault, Marta R. Costa-Jussa, Omnilingual SONAR Team: Jo\\~ao Maria Janeiro, Paul-Ambroise Duquenne, Pere-Llu\\'is Huguet Cabot, Vivek Iyer, Xiang \"Tony\" Cao, Yen Meng, Yu-An Chung","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T14:47:35Z","title":"Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16606","kind":"arxiv","version":3},"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":"sha256:011c7c6325c13cbcc288b50764f12cde4b6531dfb4329624ef122642158e8c52","target":"record","created_at":"2026-06-19T16:12:53Z","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":"1dfe66db0d1ae29669f6ad49c619f1854c2a27cb397da0f659d2b7057f8f6fba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T14:47:35Z","title_canon_sha256":"9a6b01c0febc0c8d8896355c97f598fe9829532e6bca84692f86a57cd7d2e3b5"},"schema_version":"1.0","source":{"id":"2603.16606","kind":"arxiv","version":3}},"canonical_sha256":"4c6d8725d2db90a0442f9b92545806230951445aab6a743b04c1dd0420db2f71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c6d8725d2db90a0442f9b92545806230951445aab6a743b04c1dd0420db2f71","first_computed_at":"2026-06-19T16:12:53.131606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:53.131606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OUjOLCRuNSY0xFjy1MDFGFqwx8CqXeXzh08IqwhcBIV29WpzlspwGnhOxSb5qOQLBMDMSkKESnSPxbsRL3a4Dg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:53.132133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.16606","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:011c7c6325c13cbcc288b50764f12cde4b6531dfb4329624ef122642158e8c52","sha256:8db628492ce862f57d4e90afffc9593b936ee700077a368f945a297eb675fc36"],"state_sha256":"25d94e369ab68d8b062f851ee97e3973284c45453b210fe34996665477a6af34"}