{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GENG5NZNXYGCL64JQLWDLKDIK4","short_pith_number":"pith:GENG5NZN","schema_version":"1.0","canonical_sha256":"311a6eb72dbe0c25fb8982ec35a86857347da307faebc884651459ddc6ff6cad","source":{"kind":"arxiv","id":"2605.16026","version":1},"attestation_state":"computed","paper":{"title":"From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianjun Zhao, Lei Ma, Liang Zhang, Xiongfei Wu, Yang Hou, Yu Pan, Yves Le Traon","submitted_at":"2026-05-15T15:01:45Z","abstract_excerpt":"Compositional speech-to-speech translation (S2ST) systems built upon speech large language models (SpeechLLMs) have recently shown promising performance. However, existing S2ST systems often either neglect source-language information or encode it through a language-as-label paradigm, representing each source language as an independent flat embedding. Such a design overlooks systematic linguistic structure shared across languages, which may limit data-efficient multilingual adaptation when supervised S2ST data are scarce. To address this issue, we propose S2ST-Omni 2, a many-to-one compositiona"},"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":"2605.16026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T15:01:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c983e5deb7a877271eed0cb067385714d3cf87132035338a7e55282b42324910","abstract_canon_sha256":"f84a472a84eda67c5b6decae016b5ad31e0a9df49e7924928718c3dae791b2ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:49.835963Z","signature_b64":"XVpTnTSg0v9Pr+wUy8w1GezJk68OBqsKlT8FYJWiSp/Z+28Wfn+HpdSw0OH4dKnAgE0qh1g55MOqE6j3+VFIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"311a6eb72dbe0c25fb8982ec35a86857347da307faebc884651459ddc6ff6cad","last_reissued_at":"2026-05-20T00:01:49.835248Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:49.835248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianjun Zhao, Lei Ma, Liang Zhang, Xiongfei Wu, Yang Hou, Yu Pan, Yves Le Traon","submitted_at":"2026-05-15T15:01:45Z","abstract_excerpt":"Compositional speech-to-speech translation (S2ST) systems built upon speech large language models (SpeechLLMs) have recently shown promising performance. However, existing S2ST systems often either neglect source-language information or encode it through a language-as-label paradigm, representing each source language as an independent flat embedding. Such a design overlooks systematic linguistic structure shared across languages, which may limit data-efficient multilingual adaptation when supervised S2ST data are scarce. To address this issue, we propose S2ST-Omni 2, a many-to-one compositiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16026","kind":"arxiv","version":1},"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/2605.16026/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:42.154311Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.628198Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7bf059cf69affa6afed434457d1e7f3c9ee40ff320a0468457e67c25952a44a4"},"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":"2605.16026","created_at":"2026-05-20T00:01:49.835390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16026v1","created_at":"2026-05-20T00:01:49.835390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16026","created_at":"2026-05-20T00:01:49.835390+00:00"},{"alias_kind":"pith_short_12","alias_value":"GENG5NZNXYGC","created_at":"2026-05-20T00:01:49.835390+00:00"},{"alias_kind":"pith_short_16","alias_value":"GENG5NZNXYGCL64J","created_at":"2026-05-20T00:01:49.835390+00:00"},{"alias_kind":"pith_short_8","alias_value":"GENG5NZN","created_at":"2026-05-20T00:01:49.835390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GENG5NZNXYGCL64JQLWDLKDIK4","json":"https://pith.science/pith/GENG5NZNXYGCL64JQLWDLKDIK4.json","graph_json":"https://pith.science/api/pith-number/GENG5NZNXYGCL64JQLWDLKDIK4/graph.json","events_json":"https://pith.science/api/pith-number/GENG5NZNXYGCL64JQLWDLKDIK4/events.json","paper":"https://pith.science/paper/GENG5NZN"},"agent_actions":{"view_html":"https://pith.science/pith/GENG5NZNXYGCL64JQLWDLKDIK4","download_json":"https://pith.science/pith/GENG5NZNXYGCL64JQLWDLKDIK4.json","view_paper":"https://pith.science/paper/GENG5NZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16026&json=true","fetch_graph":"https://pith.science/api/pith-number/GENG5NZNXYGCL64JQLWDLKDIK4/graph.json","fetch_events":"https://pith.science/api/pith-number/GENG5NZNXYGCL64JQLWDLKDIK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GENG5NZNXYGCL64JQLWDLKDIK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GENG5NZNXYGCL64JQLWDLKDIK4/action/storage_attestation","attest_author":"https://pith.science/pith/GENG5NZNXYGCL64JQLWDLKDIK4/action/author_attestation","sign_citation":"https://pith.science/pith/GENG5NZNXYGCL64JQLWDLKDIK4/action/citation_signature","submit_replication":"https://pith.science/pith/GENG5NZNXYGCL64JQLWDLKDIK4/action/replication_record"}},"created_at":"2026-05-20T00:01:49.835390+00:00","updated_at":"2026-05-20T00:01:49.835390+00:00"}