{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:74Z5QYSUI7PKV4M64MQRZ5NBY4","short_pith_number":"pith:74Z5QYSU","schema_version":"1.0","canonical_sha256":"ff33d8625447deaaf19ee3211cf5a1c70ab6aea84a41df8f9cd5a21a19d1acb3","source":{"kind":"arxiv","id":"2606.22983","version":1},"attestation_state":"computed","paper":{"title":"LiveServe: Interaction-Aware Serving for Real-Time Omni-Modal LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chenguang Zheng, James Cheng, Peiqi Yin, Sheng Guan, Xiangyu Zhi, Xiao Yan","submitted_at":"2026-06-22T08:04:12Z","abstract_excerpt":"Realtime omni-modal LMs support speech-centric conversations where users stream inputs, hear generated audio, and interrupt freely. Existing Omni-LM serving systems still rely on throughput-oriented LLM scheduling and LRU KV offloading. These policies ignore audio playback and multi-turn reuse: they may generate tokens far beyond what users hear, wasting work after barge-in, and evict KV state needed in the next turn. LiveServe is an interaction-aware serving system for realtime Omni-LM interaction. It exposes playback progress, speech activity, and barge-in events to the serving pipeline. The"},"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":"2606.22983","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-22T08:04:12Z","cross_cats_sorted":[],"title_canon_sha256":"67480411fda73de674b08e8bec39bbd060b06cc336c45ec2888cd85f806bb2b8","abstract_canon_sha256":"31b296286704ae0c18dcb62fec7cfa72efd123967b9680ff4510e61c9c596301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:05.934178Z","signature_b64":"KXeO+BNFVKgDJUHALOqJPN6pIDLLt5ovSgUnLUEMijzToLOAZypBJvw7Ar0LSuDwbAFDBS75BHiscSshjqnnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff33d8625447deaaf19ee3211cf5a1c70ab6aea84a41df8f9cd5a21a19d1acb3","last_reissued_at":"2026-06-23T03:14:05.933779Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:05.933779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiveServe: Interaction-Aware Serving for Real-Time Omni-Modal LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chenguang Zheng, James Cheng, Peiqi Yin, Sheng Guan, Xiangyu Zhi, Xiao Yan","submitted_at":"2026-06-22T08:04:12Z","abstract_excerpt":"Realtime omni-modal LMs support speech-centric conversations where users stream inputs, hear generated audio, and interrupt freely. Existing Omni-LM serving systems still rely on throughput-oriented LLM scheduling and LRU KV offloading. These policies ignore audio playback and multi-turn reuse: they may generate tokens far beyond what users hear, wasting work after barge-in, and evict KV state needed in the next turn. LiveServe is an interaction-aware serving system for realtime Omni-LM interaction. It exposes playback progress, speech activity, and barge-in events to the serving pipeline. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22983","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/2606.22983/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":"2606.22983","created_at":"2026-06-23T03:14:05.933835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22983v1","created_at":"2026-06-23T03:14:05.933835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22983","created_at":"2026-06-23T03:14:05.933835+00:00"},{"alias_kind":"pith_short_12","alias_value":"74Z5QYSUI7PK","created_at":"2026-06-23T03:14:05.933835+00:00"},{"alias_kind":"pith_short_16","alias_value":"74Z5QYSUI7PKV4M6","created_at":"2026-06-23T03:14:05.933835+00:00"},{"alias_kind":"pith_short_8","alias_value":"74Z5QYSU","created_at":"2026-06-23T03:14:05.933835+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/74Z5QYSUI7PKV4M64MQRZ5NBY4","json":"https://pith.science/pith/74Z5QYSUI7PKV4M64MQRZ5NBY4.json","graph_json":"https://pith.science/api/pith-number/74Z5QYSUI7PKV4M64MQRZ5NBY4/graph.json","events_json":"https://pith.science/api/pith-number/74Z5QYSUI7PKV4M64MQRZ5NBY4/events.json","paper":"https://pith.science/paper/74Z5QYSU"},"agent_actions":{"view_html":"https://pith.science/pith/74Z5QYSUI7PKV4M64MQRZ5NBY4","download_json":"https://pith.science/pith/74Z5QYSUI7PKV4M64MQRZ5NBY4.json","view_paper":"https://pith.science/paper/74Z5QYSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22983&json=true","fetch_graph":"https://pith.science/api/pith-number/74Z5QYSUI7PKV4M64MQRZ5NBY4/graph.json","fetch_events":"https://pith.science/api/pith-number/74Z5QYSUI7PKV4M64MQRZ5NBY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74Z5QYSUI7PKV4M64MQRZ5NBY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74Z5QYSUI7PKV4M64MQRZ5NBY4/action/storage_attestation","attest_author":"https://pith.science/pith/74Z5QYSUI7PKV4M64MQRZ5NBY4/action/author_attestation","sign_citation":"https://pith.science/pith/74Z5QYSUI7PKV4M64MQRZ5NBY4/action/citation_signature","submit_replication":"https://pith.science/pith/74Z5QYSUI7PKV4M64MQRZ5NBY4/action/replication_record"}},"created_at":"2026-06-23T03:14:05.933835+00:00","updated_at":"2026-06-23T03:14:05.933835+00:00"}