{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7CMJ4DTIQEF3WOEQCRAOZYOFPR","short_pith_number":"pith:7CMJ4DTI","schema_version":"1.0","canonical_sha256":"f8989e0e68810bbb38901440ece1c57c49a60bbdb4b4cb36e845d961c62f392b","source":{"kind":"arxiv","id":"2606.05121","version":1},"attestation_state":"computed","paper":{"title":"Audio Interaction Model","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":"Chunyan Miao, Deheng Ye, Dongchao Yang, Mingbao Lin, Shuicheng Yan, Xiaobin Hu, Yue Liao, Ze An, Zhifei Xie, Zihang Liu, Ziyang Ma","submitted_at":"2026-06-03T17:26:11Z","abstract_excerpt":"Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only a single task such as streaming ASR or voice chatting. It is time to unify them into one online LALM: a model that, through an always-on perceive-decide-respond loop, listens to sound, environment, and instructions in real time and reacts on the fly. We formalize this regime as the Audio Interaction Model, and realize it with Audio-Interaction, a unified streaming model that retains offline task execution while adding online general audio instruc"},"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":"2606.05121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T17:26:11Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"title_canon_sha256":"ba7bf675091c02aa93db4339689c2981fb14525d3ee6e92c9ef10189279ad942","abstract_canon_sha256":"2274bf3642325ea8c0630e851aa4372aa4e153fad6bd1635758a628cb6c2d0c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:10:07.163376Z","signature_b64":"pBfNJWCr97cZ7oi+u3cwkAfiK2tDT2pudT2MZ00k9/2je2zT1cvL639ZtaU3Ux+MhUVcG63xN9EAoaVsDvbuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8989e0e68810bbb38901440ece1c57c49a60bbdb4b4cb36e845d961c62f392b","last_reissued_at":"2026-06-04T01:10:07.162825Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:10:07.162825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Interaction Model","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":"Chunyan Miao, Deheng Ye, Dongchao Yang, Mingbao Lin, Shuicheng Yan, Xiaobin Hu, Yue Liao, Ze An, Zhifei Xie, Zihang Liu, Ziyang Ma","submitted_at":"2026-06-03T17:26:11Z","abstract_excerpt":"Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only a single task such as streaming ASR or voice chatting. It is time to unify them into one online LALM: a model that, through an always-on perceive-decide-respond loop, listens to sound, environment, and instructions in real time and reacts on the fly. We formalize this regime as the Audio Interaction Model, and realize it with Audio-Interaction, a unified streaming model that retains offline task execution while adding online general audio instruc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05121","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/2606.05121/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":"2606.05121","created_at":"2026-06-04T01:10:07.162909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05121v1","created_at":"2026-06-04T01:10:07.162909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05121","created_at":"2026-06-04T01:10:07.162909+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CMJ4DTIQEF3","created_at":"2026-06-04T01:10:07.162909+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CMJ4DTIQEF3WOEQ","created_at":"2026-06-04T01:10:07.162909+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CMJ4DTI","created_at":"2026-06-04T01:10:07.162909+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/7CMJ4DTIQEF3WOEQCRAOZYOFPR","json":"https://pith.science/pith/7CMJ4DTIQEF3WOEQCRAOZYOFPR.json","graph_json":"https://pith.science/api/pith-number/7CMJ4DTIQEF3WOEQCRAOZYOFPR/graph.json","events_json":"https://pith.science/api/pith-number/7CMJ4DTIQEF3WOEQCRAOZYOFPR/events.json","paper":"https://pith.science/paper/7CMJ4DTI"},"agent_actions":{"view_html":"https://pith.science/pith/7CMJ4DTIQEF3WOEQCRAOZYOFPR","download_json":"https://pith.science/pith/7CMJ4DTIQEF3WOEQCRAOZYOFPR.json","view_paper":"https://pith.science/paper/7CMJ4DTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05121&json=true","fetch_graph":"https://pith.science/api/pith-number/7CMJ4DTIQEF3WOEQCRAOZYOFPR/graph.json","fetch_events":"https://pith.science/api/pith-number/7CMJ4DTIQEF3WOEQCRAOZYOFPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CMJ4DTIQEF3WOEQCRAOZYOFPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CMJ4DTIQEF3WOEQCRAOZYOFPR/action/storage_attestation","attest_author":"https://pith.science/pith/7CMJ4DTIQEF3WOEQCRAOZYOFPR/action/author_attestation","sign_citation":"https://pith.science/pith/7CMJ4DTIQEF3WOEQCRAOZYOFPR/action/citation_signature","submit_replication":"https://pith.science/pith/7CMJ4DTIQEF3WOEQCRAOZYOFPR/action/replication_record"}},"created_at":"2026-06-04T01:10:07.162909+00:00","updated_at":"2026-06-04T01:10:07.162909+00:00"}