{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BCXIHRX3WODZVBGE3FJCZOJZFM","short_pith_number":"pith:BCXIHRX3","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"},"canonical_sha256":"08ae83c6fbb3879a84c4d9522cb9392b19365efe221b78f8217cd07bcc8abd21","source":{"kind":"arxiv","id":"2608.01881","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BCXIHRX3WODZVBGE3FJCZOJZFM","target":"record","payload":{"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"},"canonical_sha256":"08ae83c6fbb3879a84c4d9522cb9392b19365efe221b78f8217cd07bcc8abd21","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"},"source_kind":"arxiv","source_id":"2608.01881","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T02:07:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"REK5zjMQwDIGaAMHZsGRL5tkpE3AR6l+xtE0OC2mTsm5j7mlkg1R1o9EiS2KAp82Io3H7bfGq+C+8KoRHG2PBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:05:53.335644Z"},"content_sha256":"26e519339c344f661781c7b17f8bf5b2c16b5bd8c17bca74516a4651b76fa7b6","schema_version":"1.0","event_id":"sha256:26e519339c344f661781c7b17f8bf5b2c16b5bd8c17bca74516a4651b76fa7b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BCXIHRX3WODZVBGE3FJCZOJZFM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T02:07:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8yX0inxjqENTFnF/yWuS7J7Gf7RGqSjAY8vYP0KLZ7OlJSo/BheO75EIUEnRETlggJ+ZsbwyzcjgULc95ajlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:05:53.336532Z"},"content_sha256":"97cb6bb45d7258516109cf969dc312a7051ef0b34c4c83fbf15566f13275c34d","schema_version":"1.0","event_id":"sha256:97cb6bb45d7258516109cf969dc312a7051ef0b34c4c83fbf15566f13275c34d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/bundle.json","state_url":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/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":"2026-08-05T14:05:53Z","links":{"resolver":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM","bundle":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/bundle.json","state":"https://pith.science/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCXIHRX3WODZVBGE3FJCZOJZFM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHQfxarykMb9Iz25IpXUVUpHJJySYMSqgq+c/QCg8bUCvd+v+IManTTdfm2iDVbba8yxel/lskjhSDEbk0w6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:05:53.344625Z","bundle_sha256":"01d64fcf161dcbe0635daae47a3ede028a0239d08557621267832ee80125a2f5"}}