{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BCXIHRX3WODZVBGE3FJCZOJZFM","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":"0ea3f4e2f314957f4c9319b17987af4749d55ded65f94dfd5f160b3682016c67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-03T08:24:54Z","title_canon_sha256":"59030dd77b4f986b0c86f0e78c8d39ade192be0bc7d41dc55a4c0b4f96e03791"},"schema_version":"1.0","source":{"id":"2608.01881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01881","created_at":"2026-08-04T02:07:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01881v1","created_at":"2026-08-04T02:07:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01881","created_at":"2026-08-04T02:07:31Z"},{"alias_kind":"pith_short_12","alias_value":"BCXIHRX3WODZ","created_at":"2026-08-04T02:07:31Z"},{"alias_kind":"pith_short_16","alias_value":"BCXIHRX3WODZVBGE","created_at":"2026-08-04T02:07:31Z"},{"alias_kind":"pith_short_8","alias_value":"BCXIHRX3","created_at":"2026-08-04T02:07:31Z"}],"graph_snapshots":[{"event_id":"sha256:97cb6bb45d7258516109cf969dc312a7051ef0b34c4c83fbf15566f13275c34d","target":"graph","created_at":"2026-08-04T02:07:31Z","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/2608.01881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kun Zhan, Minghao Cai, Pan Zhou, Tian-Hao Zhang, Xin Wang, Xinyuan Qian, Yilin Ren, Yuwen Wang, Zhichao Wang, Ziyang Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-03T08:24:54Z","title":"Hear, Invoke, and Understand: A Skill-Calling Multimodal Agent for Large Audio Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01881","kind":"arxiv","version":1},"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":"sha256:26e519339c344f661781c7b17f8bf5b2c16b5bd8c17bca74516a4651b76fa7b6","target":"record","created_at":"2026-08-04T02:07:31Z","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":"0ea3f4e2f314957f4c9319b17987af4749d55ded65f94dfd5f160b3682016c67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-03T08:24:54Z","title_canon_sha256":"59030dd77b4f986b0c86f0e78c8d39ade192be0bc7d41dc55a4c0b4f96e03791"},"schema_version":"1.0","source":{"id":"2608.01881","kind":"arxiv","version":1}},"canonical_sha256":"08ae83c6fbb3879a84c4d9522cb9392b19365efe221b78f8217cd07bcc8abd21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08ae83c6fbb3879a84c4d9522cb9392b19365efe221b78f8217cd07bcc8abd21","first_computed_at":"2026-08-04T02:07:31.392186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:07:31.392186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tnKS80jQcivg1wgShhmDPnDbTrxy1d+iPIouHj+b2UOkMxCX0V8cQ/2SJVs/OcQVVmqVTPmKhkLflZ33RVAeDw==","signature_status":"signed_v1","signed_at":"2026-08-04T02:07:31.393723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26e519339c344f661781c7b17f8bf5b2c16b5bd8c17bca74516a4651b76fa7b6","sha256:97cb6bb45d7258516109cf969dc312a7051ef0b34c4c83fbf15566f13275c34d"],"state_sha256":"0689394192c1e099f29288ba34ea8c12d65c80c95ea306ef2cb76ea4673912af"}