{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ADRYX32JINCCE7KZIE6UFUI5HT","short_pith_number":"pith:ADRYX32J","schema_version":"1.0","canonical_sha256":"00e38bef494344227d59413d42d11d3cd2fdb0c711f1dba9f6f92af4ffa44de8","source":{"kind":"arxiv","id":"2606.25529","version":1},"attestation_state":"computed","paper":{"title":"STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Bei Liu, Chi-Min Chan, Chunyang Jiang, Jin Li, Long Ma, Sitong Cheng, Songjun Cao, Weihao Wu, Wei Xue, Weizhen Bian, Yike Zhang, Yiming Li","submitted_at":"2026-06-24T08:06:41Z","abstract_excerpt":"Speech-to-speech translation (S2ST) should preserve not only lexical meaning, but also expressive attributes: emotion, scenario style (e.g., news reporting vs. dramatic dialogue), and nonverbal vocalizations (NVs). Moreover, collecting cross-lingual target speech that is both translation-faithful and expressively aligned with the source is difficult at scale, making reference-based evaluation impractical. We introduce STEB (Speech-to-Speech Translation Expressiveness Benchmark), a 32.6-hour Chinese--English benchmark that evaluates both standard dimensions (translation fidelity, speaker simila"},"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":"2606.25529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-24T08:06:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c89f2b32ab638c2fac2d7d0c17ed351ade562214d79025b7cb5b90fb85389ab5","abstract_canon_sha256":"98cf921146e4fc79db3529785ecb7e04da531c48c4890d1fe8dee5716bb2a7af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:07.988700Z","signature_b64":"MbmIg/pFn0wlOACSVoYql4tOazfxJ9ef15X/Uhh7+qAtj3aUzKLW/kimpNhJqJU4KbhG5eJlmas1MbAsuEStBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00e38bef494344227d59413d42d11d3cd2fdb0c711f1dba9f6f92af4ffa44de8","last_reissued_at":"2026-06-25T01:18:07.988258Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:07.988258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Bei Liu, Chi-Min Chan, Chunyang Jiang, Jin Li, Long Ma, Sitong Cheng, Songjun Cao, Weihao Wu, Wei Xue, Weizhen Bian, Yike Zhang, Yiming Li","submitted_at":"2026-06-24T08:06:41Z","abstract_excerpt":"Speech-to-speech translation (S2ST) should preserve not only lexical meaning, but also expressive attributes: emotion, scenario style (e.g., news reporting vs. dramatic dialogue), and nonverbal vocalizations (NVs). Moreover, collecting cross-lingual target speech that is both translation-faithful and expressively aligned with the source is difficult at scale, making reference-based evaluation impractical. We introduce STEB (Speech-to-Speech Translation Expressiveness Benchmark), a 32.6-hour Chinese--English benchmark that evaluates both standard dimensions (translation fidelity, speaker simila"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25529","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/2606.25529/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":"2606.25529","created_at":"2026-06-25T01:18:07.988326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25529v1","created_at":"2026-06-25T01:18:07.988326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25529","created_at":"2026-06-25T01:18:07.988326+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADRYX32JINCC","created_at":"2026-06-25T01:18:07.988326+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADRYX32JINCCE7KZ","created_at":"2026-06-25T01:18:07.988326+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADRYX32J","created_at":"2026-06-25T01:18:07.988326+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/ADRYX32JINCCE7KZIE6UFUI5HT","json":"https://pith.science/pith/ADRYX32JINCCE7KZIE6UFUI5HT.json","graph_json":"https://pith.science/api/pith-number/ADRYX32JINCCE7KZIE6UFUI5HT/graph.json","events_json":"https://pith.science/api/pith-number/ADRYX32JINCCE7KZIE6UFUI5HT/events.json","paper":"https://pith.science/paper/ADRYX32J"},"agent_actions":{"view_html":"https://pith.science/pith/ADRYX32JINCCE7KZIE6UFUI5HT","download_json":"https://pith.science/pith/ADRYX32JINCCE7KZIE6UFUI5HT.json","view_paper":"https://pith.science/paper/ADRYX32J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25529&json=true","fetch_graph":"https://pith.science/api/pith-number/ADRYX32JINCCE7KZIE6UFUI5HT/graph.json","fetch_events":"https://pith.science/api/pith-number/ADRYX32JINCCE7KZIE6UFUI5HT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADRYX32JINCCE7KZIE6UFUI5HT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADRYX32JINCCE7KZIE6UFUI5HT/action/storage_attestation","attest_author":"https://pith.science/pith/ADRYX32JINCCE7KZIE6UFUI5HT/action/author_attestation","sign_citation":"https://pith.science/pith/ADRYX32JINCCE7KZIE6UFUI5HT/action/citation_signature","submit_replication":"https://pith.science/pith/ADRYX32JINCCE7KZIE6UFUI5HT/action/replication_record"}},"created_at":"2026-06-25T01:18:07.988326+00:00","updated_at":"2026-06-25T01:18:07.988326+00:00"}