{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XDRDHMN3T3SQAVSFP2ZCKABITF","short_pith_number":"pith:XDRDHMN3","canonical_record":{"source":{"id":"2410.17196","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T17:15:20Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"89cc10e5f8b173057e5fbfa94b77714278acfadf0e45951cd819b631a771ec77","abstract_canon_sha256":"30a1817c039a304e979ed3fd0961d078c6c729215c13cc633a1639054246f41c"},"schema_version":"1.0"},"canonical_sha256":"b8e233b1bb9ee50056457eb22500289973b4161e537385c49cc64f207385d600","source":{"kind":"arxiv","id":"2410.17196","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17196","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17196v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17196","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"XDRDHMN3T3SQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XDRDHMN3T3SQAVSF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XDRDHMN3","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XDRDHMN3T3SQAVSFP2ZCKABITF","target":"record","payload":{"canonical_record":{"source":{"id":"2410.17196","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T17:15:20Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"89cc10e5f8b173057e5fbfa94b77714278acfadf0e45951cd819b631a771ec77","abstract_canon_sha256":"30a1817c039a304e979ed3fd0961d078c6c729215c13cc633a1639054246f41c"},"schema_version":"1.0"},"canonical_sha256":"b8e233b1bb9ee50056457eb22500289973b4161e537385c49cc64f207385d600","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.069540Z","signature_b64":"PwBJYzR0knHu/L0pbaosw59UY6g9/02srse6t6K+LKLzaPcTy7OFmHI+2Kk6PhbAlqEAsk/69bqRayB2hrUwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8e233b1bb9ee50056457eb22500289973b4161e537385c49cc64f207385d600","last_reissued_at":"2026-05-17T23:38:46.069024Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.069024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.17196","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUD5h8yOzX4dIIAW3H1jJW9jtjA2KSqgAGBWuS56poCtacB3V65jY4Y66lwOqbK1PENiXN6KDef4e5Y/tcDfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:26:08.674047Z"},"content_sha256":"86046c7bb793e4eba265b0bb360b9c0ff114b82a9a2f10ef986d369f77e6e0ee","schema_version":"1.0","event_id":"sha256:86046c7bb793e4eba265b0bb360b9c0ff114b82a9a2f10ef986d369f77e6e0ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XDRDHMN3T3SQAVSFP2ZCKABITF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content.","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Haizhou Li, Robby T. Tan, Xianghu Yue, Xiaoxue Gao, Yiming Chen","submitted_at":"2024-10-22T17:15:20Z","abstract_excerpt":"Building on the success of large language models (LLMs), recent advancements such as GPT-4o have enabled real-time speech interactions through LLM-based voice assistants, offering a significantly improved user experience compared to traditional text-based interactions. However, the absence of benchmarks designed to evaluate these speech interaction capabilities has hindered progress of LLM-based voice assistants development. Current evaluations focus primarily on automatic speech recognition (ASR) or general knowledge evaluation with clean speeches, neglecting the more intricate, real-world sc"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the selected variations in speaker characteristics, environmental factors, and content factors adequately represent the intricate real-world scenarios that current evaluations neglect.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VoiceBench is the first benchmark for multi-faceted evaluation of LLM voice assistants using real and synthetic spoken instructions with speaker, environmental, and content variations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"da6901dd0f53cc640dfd4246ea233c47861fa79648cff946c80bf53476223f48"},"source":{"id":"2410.17196","kind":"arxiv","version":3},"verdict":{"id":"b4739c94-417f-4410-b0da-3ccddff6302c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T00:44:53.168044Z","strongest_claim":"We introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations.","one_line_summary":"VoiceBench is the first benchmark for multi-faceted evaluation of LLM voice assistants using real and synthetic spoken instructions with speaker, environmental, and content variations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the selected variations in speaker characteristics, environmental factors, and content factors adequately represent the intricate real-world scenarios that current evaluations neglect.","pith_extraction_headline":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content."},"references":{"count":85,"sample":[{"doi":"","year":null,"title":"Advances in Neural Information Processing Systems , volume=","work_id":"35076cd8-2723-4c99-b604-65676abad5b8","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Twelfth International Conference on Learning Representations , year=","work_id":"324853f3-6bd4-422b-b68c-2ed4fc1e0394","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Twelfth International Conference on Learning Representations , year=","work_id":"13d914fb-8f91-4a50-9c77-40b04fba8d96","ref_index":7,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1994,"title":"Preliminaries to a theory of speech disfluencies , author=. 1994 , school=","work_id":"9fb6096f-3706-4752-a22c-c88c6778e55e","ref_index":13,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Advances in neural information processing systems , volume=","work_id":"f2a4f68e-48af-40c6-90d4-76b155136aa5","ref_index":14,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":85,"snapshot_sha256":"d21bca70ec65b4bc4c5adcb504e06df5c8abbede9c390bf6f474d5ca6c2b74bb","internal_anchors":10},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5efe2de4480e92fb74930c7f438726b937bd90861ca54708e829342465816f4e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"b4739c94-417f-4410-b0da-3ccddff6302c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vQplBXCFYLvIe+98raxZg+Pw43lF+NC1VrPbNGZZOUsdFZ4yLj85/haF/S3K5LTarWQHUGTeCbC4iZtpVB7aBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:26:08.675190Z"},"content_sha256":"df3614aa9a7434958cc40f4d304cf2a250452da72e914be44119ad64f294c8e2","schema_version":"1.0","event_id":"sha256:df3614aa9a7434958cc40f4d304cf2a250452da72e914be44119ad64f294c8e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/bundle.json","state_url":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T15:26:08Z","links":{"resolver":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF","bundle":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/bundle.json","state":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XDRDHMN3T3SQAVSFP2ZCKABITF","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":"30a1817c039a304e979ed3fd0961d078c6c729215c13cc633a1639054246f41c","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T17:15:20Z","title_canon_sha256":"89cc10e5f8b173057e5fbfa94b77714278acfadf0e45951cd819b631a771ec77"},"schema_version":"1.0","source":{"id":"2410.17196","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17196","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17196v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17196","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"XDRDHMN3T3SQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XDRDHMN3T3SQAVSF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XDRDHMN3","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:df3614aa9a7434958cc40f4d304cf2a250452da72e914be44119ad64f294c8e2","target":"graph","created_at":"2026-05-17T23:38:46Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the selected variations in speaker characteristics, environmental factors, and content factors adequately represent the intricate real-world scenarios that current evaluations neglect."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VoiceBench is the first benchmark for multi-faceted evaluation of LLM voice assistants using real and synthetic spoken instructions with speaker, environmental, and content variations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content."}],"snapshot_sha256":"da6901dd0f53cc640dfd4246ea233c47861fa79648cff946c80bf53476223f48"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5efe2de4480e92fb74930c7f438726b937bd90861ca54708e829342465816f4e"},"paper":{"abstract_excerpt":"Building on the success of large language models (LLMs), recent advancements such as GPT-4o have enabled real-time speech interactions through LLM-based voice assistants, offering a significantly improved user experience compared to traditional text-based interactions. However, the absence of benchmarks designed to evaluate these speech interaction capabilities has hindered progress of LLM-based voice assistants development. Current evaluations focus primarily on automatic speech recognition (ASR) or general knowledge evaluation with clean speeches, neglecting the more intricate, real-world sc","authors_text":"Chen Zhang, Haizhou Li, Robby T. Tan, Xianghu Yue, Xiaoxue Gao, Yiming Chen","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T17:15:20Z","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants"},"references":{"count":85,"internal_anchors":10,"resolved_work":85,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Advances in Neural Information Processing Systems , volume=","work_id":"35076cd8-2723-4c99-b604-65676abad5b8","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"The Twelfth International Conference on Learning Representations , year=","work_id":"324853f3-6bd4-422b-b68c-2ed4fc1e0394","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":7,"title":"The Twelfth International Conference on Learning Representations , year=","work_id":"13d914fb-8f91-4a50-9c77-40b04fba8d96","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":13,"title":"Preliminaries to a theory of speech disfluencies , author=. 1994 , school=","work_id":"9fb6096f-3706-4752-a22c-c88c6778e55e","year":1994},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":14,"title":"Advances in neural information processing systems , volume=","work_id":"f2a4f68e-48af-40c6-90d4-76b155136aa5","year":null}],"snapshot_sha256":"d21bca70ec65b4bc4c5adcb504e06df5c8abbede9c390bf6f474d5ca6c2b74bb"},"source":{"id":"2410.17196","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T00:44:53.168044Z","id":"b4739c94-417f-4410-b0da-3ccddff6302c","model_set":{"reader":"grok-4.3"},"one_line_summary":"VoiceBench is the first benchmark for multi-faceted evaluation of LLM voice assistants using real and synthetic spoken instructions with speaker, environmental, and content variations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content.","strongest_claim":"We introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations.","weakest_assumption":"That the selected variations in speaker characteristics, environmental factors, and content factors adequately represent the intricate real-world scenarios that current evaluations neglect."}},"verdict_id":"b4739c94-417f-4410-b0da-3ccddff6302c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:86046c7bb793e4eba265b0bb360b9c0ff114b82a9a2f10ef986d369f77e6e0ee","target":"record","created_at":"2026-05-17T23:38:46Z","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":"30a1817c039a304e979ed3fd0961d078c6c729215c13cc633a1639054246f41c","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T17:15:20Z","title_canon_sha256":"89cc10e5f8b173057e5fbfa94b77714278acfadf0e45951cd819b631a771ec77"},"schema_version":"1.0","source":{"id":"2410.17196","kind":"arxiv","version":3}},"canonical_sha256":"b8e233b1bb9ee50056457eb22500289973b4161e537385c49cc64f207385d600","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8e233b1bb9ee50056457eb22500289973b4161e537385c49cc64f207385d600","first_computed_at":"2026-05-17T23:38:46.069024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.069024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PwBJYzR0knHu/L0pbaosw59UY6g9/02srse6t6K+LKLzaPcTy7OFmHI+2Kk6PhbAlqEAsk/69bqRayB2hrUwBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.069540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17196","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86046c7bb793e4eba265b0bb360b9c0ff114b82a9a2f10ef986d369f77e6e0ee","sha256:df3614aa9a7434958cc40f4d304cf2a250452da72e914be44119ad64f294c8e2"],"state_sha256":"f42bedcd2874e919e057855b2ca52bbb6bca1f99b8e06bbc80db6ec3034be36f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BbO8EQLDtu9bXlVZDwGogF6PddBAZfwNSTzb9B3eaEQmV19Tkpovx8kX/CgKRTBS7kHTyc3Vu2GFwC2KjIwUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T15:26:08.680201Z","bundle_sha256":"94c51488d561fe4003346a1939bc05a45acbe179acaa1c7bd58ed911b8ba1bca"}}