{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BCXIHRX3WODZVBGE3FJCZOJZFM","short_pith_number":"pith:BCXIHRX3","schema_version":"1.0","canonical_sha256":"08ae83c6fbb3879a84c4d9522cb9392b19365efe221b78f8217cd07bcc8abd21","source":{"kind":"arxiv","id":"2608.01881","version":1},"attestation_state":"computed","paper":{"title":"Hear, Invoke, and Understand: A Skill-Calling Multimodal Agent for Large Audio Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MM","authors_text":"Kun Zhan, Minghao Cai, Pan Zhou, Tian-Hao Zhang, Xin Wang, Xinyuan Qian, Yilin Ren, Yuwen Wang, Zhichao Wang, Ziyang Jiang","submitted_at":"2026-08-03T08:24:54Z","abstract_excerpt":"Complex acoustic problems may require models to perform acoustic operations, interact with external tools and reason over the resulting textual or processed-audio observations rather than answer directly from a fixed audio input. We study such problems as tool-interactive audio reasoning and develop SpeechAgent-R, an audio agent that coordinates its intrinsic multimodal understanding with external skills and tools. To support this capability, we construct HIU-Corpus, comprising 65,492 interaction trajectories and 507.6 hours of audio across 24 tasks, 8 skills and 9 tools. SpeechAgent-R first l"},"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":"2608.01881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-03T08:24:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"59030dd77b4f986b0c86f0e78c8d39ade192be0bc7d41dc55a4c0b4f96e03791","abstract_canon_sha256":"0ea3f4e2f314957f4c9319b17987af4749d55ded65f94dfd5f160b3682016c67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:07:31.393723Z","signature_b64":"tnKS80jQcivg1wgShhmDPnDbTrxy1d+iPIouHj+b2UOkMxCX0V8cQ/2SJVs/OcQVVmqVTPmKhkLflZ33RVAeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08ae83c6fbb3879a84c4d9522cb9392b19365efe221b78f8217cd07bcc8abd21","last_reissued_at":"2026-08-04T02:07:31.392186Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:07:31.392186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hear, Invoke, and Understand: A Skill-Calling Multimodal Agent for Large Audio Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MM","authors_text":"Kun Zhan, Minghao Cai, Pan Zhou, Tian-Hao Zhang, Xin Wang, Xinyuan Qian, Yilin Ren, Yuwen Wang, Zhichao Wang, Ziyang Jiang","submitted_at":"2026-08-03T08:24:54Z","abstract_excerpt":"Complex acoustic problems may require models to perform acoustic operations, interact with external tools and reason over the resulting textual or processed-audio observations rather than answer directly from a fixed audio input. We study such problems as tool-interactive audio reasoning and develop SpeechAgent-R, an audio agent that coordinates its intrinsic multimodal understanding with external skills and tools. To support this capability, we construct HIU-Corpus, comprising 65,492 interaction trajectories and 507.6 hours of audio across 24 tasks, 8 skills and 9 tools. SpeechAgent-R first l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01881","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/2608.01881/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":"2608.01881","created_at":"2026-08-04T02:07:31.393657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01881v1","created_at":"2026-08-04T02:07:31.393657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01881","created_at":"2026-08-04T02:07:31.393657+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCXIHRX3WODZ","created_at":"2026-08-04T02:07:31.393657+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCXIHRX3WODZVBGE","created_at":"2026-08-04T02:07:31.393657+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCXIHRX3","created_at":"2026-08-04T02:07:31.393657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM","json":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM.json","graph_json":"https://pith.science/api/pith-number/BCXIHRX3WODZVBGE3FJCZOJZFM/graph.json","events_json":"https://pith.science/api/pith-number/BCXIHRX3WODZVBGE3FJCZOJZFM/events.json","paper":"https://pith.science/paper/BCXIHRX3"},"agent_actions":{"view_html":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM","download_json":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM.json","view_paper":"https://pith.science/paper/BCXIHRX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01881&json=true","fetch_graph":"https://pith.science/api/pith-number/BCXIHRX3WODZVBGE3FJCZOJZFM/graph.json","fetch_events":"https://pith.science/api/pith-number/BCXIHRX3WODZVBGE3FJCZOJZFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/action/storage_attestation","attest_author":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/action/author_attestation","sign_citation":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/action/citation_signature","submit_replication":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/action/replication_record"}},"created_at":"2026-08-04T02:07:31.393657+00:00","updated_at":"2026-08-04T02:07:31.393657+00:00"}