{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EGJGGHV5FMRZZU7655XEOGMDES","short_pith_number":"pith:EGJGGHV5","schema_version":"1.0","canonical_sha256":"2192631ebd2b239cd3feef6e47198324a9d0157e65fd7c31efa16291f496e103","source":{"kind":"arxiv","id":"2502.17810","version":3},"attestation_state":"computed","paper":{"title":"URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Yang, Kai Yu, Ruiqi Yan, Wenxi Chen, Xie Chen, Xiquan Li, Zhikang Niu, Ziyang Ma","submitted_at":"2025-02-25T03:31:48Z","abstract_excerpt":"Recent advances in large language models (LLMs) have driven significant progress in end-to-end spoken dialogue models (SDMs). In contrast to text-based LLMs, the evaluation framework for SDMs should encompass both cognitive dimensions (e.g., logical reasoning, knowledge) and speech-related aspects (e.g., paralinguistic cues, audio quality). However, there is still a lack of comprehensive evaluations for SDMs in speech-to-speech (S2S) scenarios. To address this gap, we propose URO-Bench, an extensive benchmark for SDMs. Notably, URO-Bench is the first S2S benchmark that covers evaluations about"},"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":"2502.17810","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T03:31:48Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fb7b6a8beee3d5d6df7f20adc02215f8ec391cddddaad2a2039c7c32c52b8168","abstract_canon_sha256":"6637802e603522dc6093457b648fd94cf2e147c3aab4e0028fc385148e9cae69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:22.557735Z","signature_b64":"UrLA5iynt15VJM0FwY82cC6CBIoIpmAsDPnu+Y07F1JWy9+ZgV1qxRAzQVO0WOEsZxuYnG8ARwcVe2+zdP1WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2192631ebd2b239cd3feef6e47198324a9d0157e65fd7c31efa16291f496e103","last_reissued_at":"2026-07-05T11:51:22.557240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:22.557240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Yang, Kai Yu, Ruiqi Yan, Wenxi Chen, Xie Chen, Xiquan Li, Zhikang Niu, Ziyang Ma","submitted_at":"2025-02-25T03:31:48Z","abstract_excerpt":"Recent advances in large language models (LLMs) have driven significant progress in end-to-end spoken dialogue models (SDMs). In contrast to text-based LLMs, the evaluation framework for SDMs should encompass both cognitive dimensions (e.g., logical reasoning, knowledge) and speech-related aspects (e.g., paralinguistic cues, audio quality). However, there is still a lack of comprehensive evaluations for SDMs in speech-to-speech (S2S) scenarios. To address this gap, we propose URO-Bench, an extensive benchmark for SDMs. Notably, URO-Bench is the first S2S benchmark that covers evaluations about"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17810","kind":"arxiv","version":3},"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/2502.17810/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":"2502.17810","created_at":"2026-07-05T11:51:22.557298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17810v3","created_at":"2026-07-05T11:51:22.557298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17810","created_at":"2026-07-05T11:51:22.557298+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGJGGHV5FMRZ","created_at":"2026-07-05T11:51:22.557298+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGJGGHV5FMRZZU76","created_at":"2026-07-05T11:51:22.557298+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGJGGHV5","created_at":"2026-07-05T11:51:22.557298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05896","citing_title":"Resonant Minds: Closed-Loop Social Avatars with Theory of Mind","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07547","citing_title":"Liberating LLM Capabilities in Full-Duplex Speech Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01016","citing_title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15957","citing_title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":181,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21008","citing_title":"A Survey of Audio Reasoning in Multimodal Foundation Models","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26388","citing_title":"Game-Time: Evaluating Temporal Dynamics in Spoken Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09592","citing_title":"Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09413","citing_title":"Evaluating the Expressive Appropriateness of Speech in Rich Contexts","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15804","citing_title":"Qwen3.5-Omni Technical Report","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGJGGHV5FMRZZU7655XEOGMDES","json":"https://pith.science/pith/EGJGGHV5FMRZZU7655XEOGMDES.json","graph_json":"https://pith.science/api/pith-number/EGJGGHV5FMRZZU7655XEOGMDES/graph.json","events_json":"https://pith.science/api/pith-number/EGJGGHV5FMRZZU7655XEOGMDES/events.json","paper":"https://pith.science/paper/EGJGGHV5"},"agent_actions":{"view_html":"https://pith.science/pith/EGJGGHV5FMRZZU7655XEOGMDES","download_json":"https://pith.science/pith/EGJGGHV5FMRZZU7655XEOGMDES.json","view_paper":"https://pith.science/paper/EGJGGHV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17810&json=true","fetch_graph":"https://pith.science/api/pith-number/EGJGGHV5FMRZZU7655XEOGMDES/graph.json","fetch_events":"https://pith.science/api/pith-number/EGJGGHV5FMRZZU7655XEOGMDES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGJGGHV5FMRZZU7655XEOGMDES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGJGGHV5FMRZZU7655XEOGMDES/action/storage_attestation","attest_author":"https://pith.science/pith/EGJGGHV5FMRZZU7655XEOGMDES/action/author_attestation","sign_citation":"https://pith.science/pith/EGJGGHV5FMRZZU7655XEOGMDES/action/citation_signature","submit_replication":"https://pith.science/pith/EGJGGHV5FMRZZU7655XEOGMDES/action/replication_record"}},"created_at":"2026-07-05T11:51:22.557298+00:00","updated_at":"2026-07-05T11:51:22.557298+00:00"}