{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EGJGGHV5FMRZZU7655XEOGMDES","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":"6637802e603522dc6093457b648fd94cf2e147c3aab4e0028fc385148e9cae69","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T03:31:48Z","title_canon_sha256":"fb7b6a8beee3d5d6df7f20adc02215f8ec391cddddaad2a2039c7c32c52b8168"},"schema_version":"1.0","source":{"id":"2502.17810","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17810","created_at":"2026-07-05T11:51:22Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17810v3","created_at":"2026-07-05T11:51:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17810","created_at":"2026-07-05T11:51:22Z"},{"alias_kind":"pith_short_12","alias_value":"EGJGGHV5FMRZ","created_at":"2026-07-05T11:51:22Z"},{"alias_kind":"pith_short_16","alias_value":"EGJGGHV5FMRZZU76","created_at":"2026-07-05T11:51:22Z"},{"alias_kind":"pith_short_8","alias_value":"EGJGGHV5","created_at":"2026-07-05T11:51:22Z"}],"graph_snapshots":[{"event_id":"sha256:1957cf6ed1d3a4435b5464cd7a796467b60f9204a68ecd7627f41276c2f05866","target":"graph","created_at":"2026-07-05T11:51:22Z","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/2502.17810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chen Yang, Kai Yu, Ruiqi Yan, Wenxi Chen, Xie Chen, Xiquan Li, Zhikang Niu, Ziyang Ma","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T03:31:48Z","title":"URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17810","kind":"arxiv","version":3},"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:a40733424812e5ac9c0d562d1b7274f8a8e0e3521e377d45da545372b48c2c90","target":"record","created_at":"2026-07-05T11:51:22Z","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":"6637802e603522dc6093457b648fd94cf2e147c3aab4e0028fc385148e9cae69","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T03:31:48Z","title_canon_sha256":"fb7b6a8beee3d5d6df7f20adc02215f8ec391cddddaad2a2039c7c32c52b8168"},"schema_version":"1.0","source":{"id":"2502.17810","kind":"arxiv","version":3}},"canonical_sha256":"2192631ebd2b239cd3feef6e47198324a9d0157e65fd7c31efa16291f496e103","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2192631ebd2b239cd3feef6e47198324a9d0157e65fd7c31efa16291f496e103","first_computed_at":"2026-07-05T11:51:22.557240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:22.557240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UrLA5iynt15VJM0FwY82cC6CBIoIpmAsDPnu+Y07F1JWy9+ZgV1qxRAzQVO0WOEsZxuYnG8ARwcVe2+zdP1WCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:22.557735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17810","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a40733424812e5ac9c0d562d1b7274f8a8e0e3521e377d45da545372b48c2c90","sha256:1957cf6ed1d3a4435b5464cd7a796467b60f9204a68ecd7627f41276c2f05866"],"state_sha256":"64979f021ad0350c066c685975c9ef545dfb220276498f2884bb840eafc82b71"}