{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OUBJTPRDCYD3FIYBU4N674QQX4","short_pith_number":"pith:OUBJTPRD","schema_version":"1.0","canonical_sha256":"750299be231607b2a301a71beff210bf0ffce1b2a8283342a017ad19a350701d","source":{"kind":"arxiv","id":"2409.18680","version":3},"attestation_state":"computed","paper":{"title":"Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Haizhou Li, Luis Fernando D'Haro, Robby T. Tan, Xianghu Yue, Xiaoxue Gao, Yiming Chen","submitted_at":"2024-09-27T12:06:53Z","abstract_excerpt":"Various audio-LLMs (ALLMs) have been explored recently for tackling different audio tasks simultaneously using a single, unified model. While existing evaluations of ALLMs primarily focus on single-audio tasks, real-world applications often involve processing multiple audio streams simultaneously. To bridge this gap, we propose the first multi-audio evaluation (MAE) benchmark that consists of 20 datasets from 11 multi-audio tasks encompassing both speech and sound scenarios. Comprehensive experiments on MAE demonstrate that the existing ALLMs, while being powerful in comprehending primary audi"},"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":"2409.18680","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-27T12:06:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"title_canon_sha256":"a3b40eca61b75132275eca15777602ef40d186e71ffa669c12f4dac67c6fcea0","abstract_canon_sha256":"7c483dc384cd07ffa0c55218b824427f2eb0d5c2ff7b4932d2bf1a3a2eb7157b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:48.931128Z","signature_b64":"U07tuvZsgze2w97Cg4h7drnYent8erYW2h0ac90nwHHRGg/EUpZIsjIMJ5YIi7KeKBWX0WnBU2cOA2J2oPWjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"750299be231607b2a301a71beff210bf0ffce1b2a8283342a017ad19a350701d","last_reissued_at":"2026-07-05T09:31:48.930593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:48.930593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Haizhou Li, Luis Fernando D'Haro, Robby T. Tan, Xianghu Yue, Xiaoxue Gao, Yiming Chen","submitted_at":"2024-09-27T12:06:53Z","abstract_excerpt":"Various audio-LLMs (ALLMs) have been explored recently for tackling different audio tasks simultaneously using a single, unified model. While existing evaluations of ALLMs primarily focus on single-audio tasks, real-world applications often involve processing multiple audio streams simultaneously. To bridge this gap, we propose the first multi-audio evaluation (MAE) benchmark that consists of 20 datasets from 11 multi-audio tasks encompassing both speech and sound scenarios. Comprehensive experiments on MAE demonstrate that the existing ALLMs, while being powerful in comprehending primary audi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18680","kind":"arxiv","version":3},"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/2409.18680/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":"2409.18680","created_at":"2026-07-05T09:31:48.930660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18680v3","created_at":"2026-07-05T09:31:48.930660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18680","created_at":"2026-07-05T09:31:48.930660+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUBJTPRDCYD3","created_at":"2026-07-05T09:31:48.930660+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUBJTPRDCYD3FIYB","created_at":"2026-07-05T09:31:48.930660+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUBJTPRD","created_at":"2026-07-05T09:31:48.930660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24044","citing_title":"RED: Adaptive Real-Time DAG Scheduling for Robotic Inference under Environmental Dynamics","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2410.17196","citing_title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUBJTPRDCYD3FIYBU4N674QQX4","json":"https://pith.science/pith/OUBJTPRDCYD3FIYBU4N674QQX4.json","graph_json":"https://pith.science/api/pith-number/OUBJTPRDCYD3FIYBU4N674QQX4/graph.json","events_json":"https://pith.science/api/pith-number/OUBJTPRDCYD3FIYBU4N674QQX4/events.json","paper":"https://pith.science/paper/OUBJTPRD"},"agent_actions":{"view_html":"https://pith.science/pith/OUBJTPRDCYD3FIYBU4N674QQX4","download_json":"https://pith.science/pith/OUBJTPRDCYD3FIYBU4N674QQX4.json","view_paper":"https://pith.science/paper/OUBJTPRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18680&json=true","fetch_graph":"https://pith.science/api/pith-number/OUBJTPRDCYD3FIYBU4N674QQX4/graph.json","fetch_events":"https://pith.science/api/pith-number/OUBJTPRDCYD3FIYBU4N674QQX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUBJTPRDCYD3FIYBU4N674QQX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUBJTPRDCYD3FIYBU4N674QQX4/action/storage_attestation","attest_author":"https://pith.science/pith/OUBJTPRDCYD3FIYBU4N674QQX4/action/author_attestation","sign_citation":"https://pith.science/pith/OUBJTPRDCYD3FIYBU4N674QQX4/action/citation_signature","submit_replication":"https://pith.science/pith/OUBJTPRDCYD3FIYBU4N674QQX4/action/replication_record"}},"created_at":"2026-07-05T09:31:48.930660+00:00","updated_at":"2026-07-05T09:31:48.930660+00:00"}