{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HVZBCHBGRKUBUG7W5XAMH4HBSM","short_pith_number":"pith:HVZBCHBG","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"},"canonical_sha256":"3d72111c268aa81a1bf6edc0c3f0e193314b9d6de97ee44f9320d6a13eb3ab2f","source":{"kind":"arxiv","id":"2501.04962","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HVZBCHBGRKUBUG7W5XAMH4HBSM","target":"record","payload":{"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"},"canonical_sha256":"3d72111c268aa81a1bf6edc0c3f0e193314b9d6de97ee44f9320d6a13eb3ab2f","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"},"source_kind":"arxiv","source_id":"2501.04962","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fOyDDj7hh6EOFj3iRf8DndWC5RHWFdy/qsExKmrM0ijbhVv09Ocvs9IX12h0XC3zKQ4pKpmgB6OUY79p4akxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:52:28.036431Z"},"content_sha256":"f0fca2334929e07e930aa636445d94bbf56c50bacd97bf36bbf535a32e734920","schema_version":"1.0","event_id":"sha256:f0fca2334929e07e930aa636445d94bbf56c50bacd97bf36bbf535a32e734920"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HVZBCHBGRKUBUG7W5XAMH4HBSM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jOOnztCbxcRabJnnOe6+wxtt0mm3qVSqJRlL2KIrdITyGl2m/wCjknrfi6AwzflLcaMnTLvxr6mBKQVxGem6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:52:28.036924Z"},"content_sha256":"50102d471fff58578212208868c4ff284e81149e5b1a7d981411942d3aff8d94","schema_version":"1.0","event_id":"sha256:50102d471fff58578212208868c4ff284e81149e5b1a7d981411942d3aff8d94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/bundle.json","state_url":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/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":"2026-08-08T08:52:28Z","links":{"resolver":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM","bundle":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/bundle.json","state":"https://pith.science/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HVZBCHBGRKUBUG7W5XAMH4HBSM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kr+Ni24fQlKzfjoqbZWXuGNaNOF8PQgfEerbc1iNx+zHdtJIZc7EUrli5TiOAx0mNHVtqxcakp3Mwex3FI9SDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:52:28.040583Z","bundle_sha256":"3e87daa984ace85992ecd8f36926940f6ec2b3e83a2df670209412f4b72680d0"}}