{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HVZBCHBGRKUBUG7W5XAMH4HBSM","short_pith_number":"pith:HVZBCHBG","schema_version":"1.0","canonical_sha256":"3d72111c268aa81a1bf6edc0c3f0e193314b9d6de97ee44f9320d6a13eb3ab2f","source":{"kind":"arxiv","id":"2501.04962","version":4},"attestation_state":"computed","paper":{"title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Irwin King, Wenqian Cui, Xiaoqi Jiao, Ziqiao Meng","submitted_at":"2025-01-09T04:30:12Z","abstract_excerpt":"With the rising need for speech-based interaction models, end-to-end Spoken Language Models (SLMs) have emerged as a promising solution. While these models require comprehensive world knowledge for meaningful and reliable human interactions, existing question-answering (QA) benchmarks fall short in evaluating SLMs' knowledge understanding due to their inability to support end-to-end speech evaluation and account for varied input audio conditions. To address these limitations, we present VoxEval, a novel SpeechQA benchmark that assesses SLMs' knowledge understanding through pure speech interact"},"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":"2501.04962","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T04:30:12Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"dfec6e9f7b90bc14b7717077d09ef62458826055d2dfb4d7df22926f819cf789","abstract_canon_sha256":"60ff4627b1bea3d083a20ab935f720daa26120053351bd010a3601dcb9ebd7b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:34.156658Z","signature_b64":"E5wxKZ87sXmYR+6zHg1A9+OyenIZCbWpzMTIncc+wWrkVblLNzIFYi/PgvVJWeKn2to99017jt56YKxd5VRcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d72111c268aa81a1bf6edc0c3f0e193314b9d6de97ee44f9320d6a13eb3ab2f","last_reissued_at":"2026-07-05T11:10:34.156172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:34.156172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Irwin King, Wenqian Cui, Xiaoqi Jiao, Ziqiao Meng","submitted_at":"2025-01-09T04:30:12Z","abstract_excerpt":"With the rising need for speech-based interaction models, end-to-end Spoken Language Models (SLMs) have emerged as a promising solution. While these models require comprehensive world knowledge for meaningful and reliable human interactions, existing question-answering (QA) benchmarks fall short in evaluating SLMs' knowledge understanding due to their inability to support end-to-end speech evaluation and account for varied input audio conditions. To address these limitations, we present VoxEval, a novel SpeechQA benchmark that assesses SLMs' knowledge understanding through pure speech interact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04962","kind":"arxiv","version":4},"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/2501.04962/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":"2501.04962","created_at":"2026-07-05T11:10:34.156229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04962v4","created_at":"2026-07-05T11:10:34.156229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04962","created_at":"2026-07-05T11:10:34.156229+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVZBCHBGRKUB","created_at":"2026-07-05T11:10:34.156229+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVZBCHBGRKUBUG7W","created_at":"2026-07-05T11:10:34.156229+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVZBCHBG","created_at":"2026-07-05T11:10:34.156229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.15957","citing_title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17225","citing_title":"Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM","json":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM.json","graph_json":"https://pith.science/api/pith-number/HVZBCHBGRKUBUG7W5XAMH4HBSM/graph.json","events_json":"https://pith.science/api/pith-number/HVZBCHBGRKUBUG7W5XAMH4HBSM/events.json","paper":"https://pith.science/paper/HVZBCHBG"},"agent_actions":{"view_html":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM","download_json":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM.json","view_paper":"https://pith.science/paper/HVZBCHBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04962&json=true","fetch_graph":"https://pith.science/api/pith-number/HVZBCHBGRKUBUG7W5XAMH4HBSM/graph.json","fetch_events":"https://pith.science/api/pith-number/HVZBCHBGRKUBUG7W5XAMH4HBSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/action/storage_attestation","attest_author":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/action/author_attestation","sign_citation":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/action/citation_signature","submit_replication":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/action/replication_record"}},"created_at":"2026-07-05T11:10:34.156229+00:00","updated_at":"2026-07-05T11:10:34.156229+00:00"}