{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HVZBCHBGRKUBUG7W5XAMH4HBSM","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":"60ff4627b1bea3d083a20ab935f720daa26120053351bd010a3601dcb9ebd7b0","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T04:30:12Z","title_canon_sha256":"dfec6e9f7b90bc14b7717077d09ef62458826055d2dfb4d7df22926f819cf789"},"schema_version":"1.0","source":{"id":"2501.04962","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04962","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04962v4","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04962","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"HVZBCHBGRKUB","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"HVZBCHBGRKUBUG7W","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"HVZBCHBG","created_at":"2026-07-05T11:10:34Z"}],"graph_snapshots":[{"event_id":"sha256:50102d471fff58578212208868c4ff284e81149e5b1a7d981411942d3aff8d94","target":"graph","created_at":"2026-07-05T11:10:34Z","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/2501.04962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Irwin King, Wenqian Cui, Xiaoqi Jiao, Ziqiao Meng","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T04:30:12Z","title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04962","kind":"arxiv","version":4},"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:f0fca2334929e07e930aa636445d94bbf56c50bacd97bf36bbf535a32e734920","target":"record","created_at":"2026-07-05T11:10:34Z","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":"60ff4627b1bea3d083a20ab935f720daa26120053351bd010a3601dcb9ebd7b0","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T04:30:12Z","title_canon_sha256":"dfec6e9f7b90bc14b7717077d09ef62458826055d2dfb4d7df22926f819cf789"},"schema_version":"1.0","source":{"id":"2501.04962","kind":"arxiv","version":4}},"canonical_sha256":"3d72111c268aa81a1bf6edc0c3f0e193314b9d6de97ee44f9320d6a13eb3ab2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d72111c268aa81a1bf6edc0c3f0e193314b9d6de97ee44f9320d6a13eb3ab2f","first_computed_at":"2026-07-05T11:10:34.156172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:34.156172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E5wxKZ87sXmYR+6zHg1A9+OyenIZCbWpzMTIncc+wWrkVblLNzIFYi/PgvVJWeKn2to99017jt56YKxd5VRcCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:34.156658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04962","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0fca2334929e07e930aa636445d94bbf56c50bacd97bf36bbf535a32e734920","sha256:50102d471fff58578212208868c4ff284e81149e5b1a7d981411942d3aff8d94"],"state_sha256":"4f480f6b33c1f77a1f754f36f6da447ca1f58116ecde4de0f53554aa6ffeec37"}