{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7CMJ4DTIQEF3WOEQCRAOZYOFPR","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":"2274bf3642325ea8c0630e851aa4372aa4e153fad6bd1635758a628cb6c2d0c9","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T17:26:11Z","title_canon_sha256":"ba7bf675091c02aa93db4339689c2981fb14525d3ee6e92c9ef10189279ad942"},"schema_version":"1.0","source":{"id":"2606.05121","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05121","created_at":"2026-06-04T01:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05121v1","created_at":"2026-06-04T01:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05121","created_at":"2026-06-04T01:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"7CMJ4DTIQEF3","created_at":"2026-06-04T01:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"7CMJ4DTIQEF3WOEQ","created_at":"2026-06-04T01:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"7CMJ4DTI","created_at":"2026-06-04T01:10:07Z"}],"graph_snapshots":[{"event_id":"sha256:1d393396a4185c1b5fe6c7a3bf6428e52156ae868fdb738706ce30699e575fba","target":"graph","created_at":"2026-06-04T01:10:07Z","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/2606.05121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chunyan Miao, Deheng Ye, Dongchao Yang, Mingbao Lin, Shuicheng Yan, Xiaobin Hu, Yue Liao, Ze An, Zhifei Xie, Zihang Liu, Ziyang Ma","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T17:26:11Z","title":"Audio Interaction Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05121","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":"sha256:50d102379efda7e76e46b685fc67f9b87c7de27a7629ba6fc4289567c1e0c872","target":"record","created_at":"2026-06-04T01:10:07Z","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":"2274bf3642325ea8c0630e851aa4372aa4e153fad6bd1635758a628cb6c2d0c9","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T17:26:11Z","title_canon_sha256":"ba7bf675091c02aa93db4339689c2981fb14525d3ee6e92c9ef10189279ad942"},"schema_version":"1.0","source":{"id":"2606.05121","kind":"arxiv","version":1}},"canonical_sha256":"f8989e0e68810bbb38901440ece1c57c49a60bbdb4b4cb36e845d961c62f392b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8989e0e68810bbb38901440ece1c57c49a60bbdb4b4cb36e845d961c62f392b","first_computed_at":"2026-06-04T01:10:07.162825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:10:07.162825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pBfNJWCr97cZ7oi+u3cwkAfiK2tDT2pudT2MZ00k9/2je2zT1cvL639ZtaU3Ux+MhUVcG63xN9EAoaVsDvbuCQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:10:07.163376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05121","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50d102379efda7e76e46b685fc67f9b87c7de27a7629ba6fc4289567c1e0c872","sha256:1d393396a4185c1b5fe6c7a3bf6428e52156ae868fdb738706ce30699e575fba"],"state_sha256":"d3ec9e80c6ce1051c02297c24a805519adbaaf39f61c3eda805cac0885b6afba"}