{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VMPRIPGKZT65TBFPWQAUAUYYSH","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":"b846c36ac8a6df73497f6086991b02095a97813cb85b617d55165b7693f11d6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-22T14:25:15Z","title_canon_sha256":"ebc295aa55cb6733847a6ff72f435e5c25c3e9cd3193d8ff002cd7a21d05f2ba"},"schema_version":"1.0","source":{"id":"2308.11466","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11466","created_at":"2026-07-05T06:43:52Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11466v2","created_at":"2026-07-05T06:43:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11466","created_at":"2026-07-05T06:43:52Z"},{"alias_kind":"pith_short_12","alias_value":"VMPRIPGKZT65","created_at":"2026-07-05T06:43:52Z"},{"alias_kind":"pith_short_16","alias_value":"VMPRIPGKZT65TBFP","created_at":"2026-07-05T06:43:52Z"},{"alias_kind":"pith_short_8","alias_value":"VMPRIPGK","created_at":"2026-07-05T06:43:52Z"}],"graph_snapshots":[{"event_id":"sha256:645a03b70d650665df7232fe7b44895c5c7abb278c6fa2b3894757dfd2e68c52","target":"graph","created_at":"2026-07-05T06:43:52Z","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/2308.11466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce SONAR, a new multilingual and multimodal fixed-size sentence embedding space. Our single text encoder, covering 200 languages, substantially outperforms existing sentence embeddings such as LASER3 and LabSE on the xsim and xsim++ multilingual similarity search tasks. Speech segments can be embedded in the same SONAR embedding space using language-specific speech encoders trained in a teacher-student setting on speech transcription data. Our encoders outperform existing speech encoders on similarity search tasks. We also provide a text decoder for 200 languages, which allows us to ","authors_text":"Beno\\^it Sagot, Holger Schwenk, Paul-Ambroise Duquenne","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-22T14:25:15Z","title":"SONAR: Sentence-Level Multimodal and Language-Agnostic Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11466","kind":"arxiv","version":2},"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:e9d2567fd985c6eeda4d30238c1b12290eefb3652db030fd7c9ac5d1e931ac44","target":"record","created_at":"2026-07-05T06:43:52Z","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":"b846c36ac8a6df73497f6086991b02095a97813cb85b617d55165b7693f11d6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-22T14:25:15Z","title_canon_sha256":"ebc295aa55cb6733847a6ff72f435e5c25c3e9cd3193d8ff002cd7a21d05f2ba"},"schema_version":"1.0","source":{"id":"2308.11466","kind":"arxiv","version":2}},"canonical_sha256":"ab1f143ccaccfdd984afb40140531891ca1bd0fa375532e4e9e86f5c8c196dd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab1f143ccaccfdd984afb40140531891ca1bd0fa375532e4e9e86f5c8c196dd9","first_computed_at":"2026-07-05T06:43:52.094532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:52.094532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kw5v77AHsQUl+P2l1i9peUHeWEeOmGtGEY3hJVS2Uim1iEz/oblrer/4pd2skmhLUweRfsbLC8OelSfcDNR9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:52.095035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.11466","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9d2567fd985c6eeda4d30238c1b12290eefb3652db030fd7c9ac5d1e931ac44","sha256:645a03b70d650665df7232fe7b44895c5c7abb278c6fa2b3894757dfd2e68c52"],"state_sha256":"a40cde6620465147939ebc1d0afd5dcdd79a4bb837c275c1a70891b6b4dca9b3"}