{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5BC4R2YB4UWCPJEGI2O3RNSWGO","short_pith_number":"pith:5BC4R2YB","schema_version":"1.0","canonical_sha256":"e845c8eb01e52c27a486469db8b65633be34d77cc380bd5d4e1f146301007a89","source":{"kind":"arxiv","id":"2606.03241","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Speech-to-Speech Translation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Alkis Koudounas, Emiru Tsunoo, Hayato Futami, Osamu Take, Quentin Jodelet, Shinji Watanabe","submitted_at":"2026-06-02T07:01:33Z","abstract_excerpt":"Speech-to-speech translation (S2ST) has advanced rapidly, but offline evaluation lacks a unified protocol: studies report non-overlapping metric subsets, preventing direct comparisons. We introduce COMPASS, a unified and reproducible benchmarking framework integrating 46 metrics across eight dimensions, and deploy it on 1,248 model-language configurations from FLEURS and CVSS, spanning cascaded and end-to-end architectures over ten language pairs. Architectures exhibit complementary strengths: best-vs-worst gaps exceed 30\\% on naturalness and speaker preservation but remain within a few points"},"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":"2606.03241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T07:01:33Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f48abbd92e834dd130e85c151de27e9bbc5bfbd9191f45f92788a50aedcbfaae","abstract_canon_sha256":"25a24be0a0555805091cdfb0092fb106f98dc2f3892d0da064d014ef090ae554"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:35.959241Z","signature_b64":"sItyhTqZvjqmOTgKrm0pXRc/gSUs+t/eg5ZHBDTJS0NbljZtqnfmHQFIT7YZhtBlk14DKoq8+y4utrhaOq3LCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e845c8eb01e52c27a486469db8b65633be34d77cc380bd5d4e1f146301007a89","last_reissued_at":"2026-06-03T01:05:35.958825Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:35.958825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Speech-to-Speech Translation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Alkis Koudounas, Emiru Tsunoo, Hayato Futami, Osamu Take, Quentin Jodelet, Shinji Watanabe","submitted_at":"2026-06-02T07:01:33Z","abstract_excerpt":"Speech-to-speech translation (S2ST) has advanced rapidly, but offline evaluation lacks a unified protocol: studies report non-overlapping metric subsets, preventing direct comparisons. We introduce COMPASS, a unified and reproducible benchmarking framework integrating 46 metrics across eight dimensions, and deploy it on 1,248 model-language configurations from FLEURS and CVSS, spanning cascaded and end-to-end architectures over ten language pairs. Architectures exhibit complementary strengths: best-vs-worst gaps exceed 30\\% on naturalness and speaker preservation but remain within a few points"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03241","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/2606.03241/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2606.03241","created_at":"2026-06-03T01:05:35.958882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03241v1","created_at":"2026-06-03T01:05:35.958882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03241","created_at":"2026-06-03T01:05:35.958882+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BC4R2YB4UWC","created_at":"2026-06-03T01:05:35.958882+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BC4R2YB4UWCPJEG","created_at":"2026-06-03T01:05:35.958882+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BC4R2YB","created_at":"2026-06-03T01:05:35.958882+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/5BC4R2YB4UWCPJEGI2O3RNSWGO","json":"https://pith.science/pith/5BC4R2YB4UWCPJEGI2O3RNSWGO.json","graph_json":"https://pith.science/api/pith-number/5BC4R2YB4UWCPJEGI2O3RNSWGO/graph.json","events_json":"https://pith.science/api/pith-number/5BC4R2YB4UWCPJEGI2O3RNSWGO/events.json","paper":"https://pith.science/paper/5BC4R2YB"},"agent_actions":{"view_html":"https://pith.science/pith/5BC4R2YB4UWCPJEGI2O3RNSWGO","download_json":"https://pith.science/pith/5BC4R2YB4UWCPJEGI2O3RNSWGO.json","view_paper":"https://pith.science/paper/5BC4R2YB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03241&json=true","fetch_graph":"https://pith.science/api/pith-number/5BC4R2YB4UWCPJEGI2O3RNSWGO/graph.json","fetch_events":"https://pith.science/api/pith-number/5BC4R2YB4UWCPJEGI2O3RNSWGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BC4R2YB4UWCPJEGI2O3RNSWGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BC4R2YB4UWCPJEGI2O3RNSWGO/action/storage_attestation","attest_author":"https://pith.science/pith/5BC4R2YB4UWCPJEGI2O3RNSWGO/action/author_attestation","sign_citation":"https://pith.science/pith/5BC4R2YB4UWCPJEGI2O3RNSWGO/action/citation_signature","submit_replication":"https://pith.science/pith/5BC4R2YB4UWCPJEGI2O3RNSWGO/action/replication_record"}},"created_at":"2026-06-03T01:05:35.958882+00:00","updated_at":"2026-06-03T01:05:35.958882+00:00"}