{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CWKKGEYQDYZW3SMK63L76IYN2K","short_pith_number":"pith:CWKKGEYQ","schema_version":"1.0","canonical_sha256":"1594a313101e336dc98af6d7ff230dd2939bb8f8aa2dae47c4badf04c3a5783d","source":{"kind":"arxiv","id":"2508.08155","version":1},"attestation_state":"computed","paper":{"title":"MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengyou Wang, Lei Xie, Shuai Wang, Zhaokai Sun, Zhennan Lin, Zhou Pan","submitted_at":"2025-08-11T16:31:32Z","abstract_excerpt":"Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the challenges posed by multi-speaker conversations that are common in real-world scenarios. We introduce MSU-Bench, a comprehensive benchmark for evaluating multi-speaker conversational understanding with a speaker-centric design. Our hierarchical framework covers four progressive tiers: single-speaker static attribute understanding, single-speaker dynamic attribute un"},"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":"2508.08155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-11T16:31:32Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"50fe887fc588fca9556e0ec57fc8d082a232ede367f91e50e939ce9591ae1b7a","abstract_canon_sha256":"2ef69232f6c3f92b679b179e9b97484fd155e6e9f1a5607f06b398bc17e0165c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:09.134664Z","signature_b64":"4mvUGXmfaiApbEo2RSJRNPukniHUMa7x6kJZWq16zKbbGuL11+Z3Qw1s1sl7vp2U89cRjJnGA+UkhAb6r/nXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1594a313101e336dc98af6d7ff230dd2939bb8f8aa2dae47c4badf04c3a5783d","last_reissued_at":"2026-07-05T11:52:09.134237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:09.134237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengyou Wang, Lei Xie, Shuai Wang, Zhaokai Sun, Zhennan Lin, Zhou Pan","submitted_at":"2025-08-11T16:31:32Z","abstract_excerpt":"Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the challenges posed by multi-speaker conversations that are common in real-world scenarios. We introduce MSU-Bench, a comprehensive benchmark for evaluating multi-speaker conversational understanding with a speaker-centric design. Our hierarchical framework covers four progressive tiers: single-speaker static attribute understanding, single-speaker dynamic attribute un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08155","kind":"arxiv","version":1},"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/2508.08155/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":"2508.08155","created_at":"2026-07-05T11:52:09.134292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08155v1","created_at":"2026-07-05T11:52:09.134292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08155","created_at":"2026-07-05T11:52:09.134292+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWKKGEYQDYZW","created_at":"2026-07-05T11:52:09.134292+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWKKGEYQDYZW3SMK","created_at":"2026-07-05T11:52:09.134292+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWKKGEYQ","created_at":"2026-07-05T11:52:09.134292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23313","citing_title":"Uncertainty-based Debiasing and Unlearning for Decontamination","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28480","citing_title":"Audio-Mind: An Auditable Agentic Framework for Audio Understanding","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17358","citing_title":"Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWKKGEYQDYZW3SMK63L76IYN2K","json":"https://pith.science/pith/CWKKGEYQDYZW3SMK63L76IYN2K.json","graph_json":"https://pith.science/api/pith-number/CWKKGEYQDYZW3SMK63L76IYN2K/graph.json","events_json":"https://pith.science/api/pith-number/CWKKGEYQDYZW3SMK63L76IYN2K/events.json","paper":"https://pith.science/paper/CWKKGEYQ"},"agent_actions":{"view_html":"https://pith.science/pith/CWKKGEYQDYZW3SMK63L76IYN2K","download_json":"https://pith.science/pith/CWKKGEYQDYZW3SMK63L76IYN2K.json","view_paper":"https://pith.science/paper/CWKKGEYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08155&json=true","fetch_graph":"https://pith.science/api/pith-number/CWKKGEYQDYZW3SMK63L76IYN2K/graph.json","fetch_events":"https://pith.science/api/pith-number/CWKKGEYQDYZW3SMK63L76IYN2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWKKGEYQDYZW3SMK63L76IYN2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWKKGEYQDYZW3SMK63L76IYN2K/action/storage_attestation","attest_author":"https://pith.science/pith/CWKKGEYQDYZW3SMK63L76IYN2K/action/author_attestation","sign_citation":"https://pith.science/pith/CWKKGEYQDYZW3SMK63L76IYN2K/action/citation_signature","submit_replication":"https://pith.science/pith/CWKKGEYQDYZW3SMK63L76IYN2K/action/replication_record"}},"created_at":"2026-07-05T11:52:09.134292+00:00","updated_at":"2026-07-05T11:52:09.134292+00:00"}