{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KOPZRQVT5ZNE74YQS4AALP74BN","short_pith_number":"pith:KOPZRQVT","schema_version":"1.0","canonical_sha256":"539f98c2b3ee5a4ff310970005bffc0b59e003ccee81563dd2addf58c034d3f4","source":{"kind":"arxiv","id":"2607.02640","version":1},"attestation_state":"computed","paper":{"title":"Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.SD","authors_text":"Bojie Li, Jiaying Meng","submitted_at":"2026-07-02T15:59:01Z","abstract_excerpt":"Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming audio and must respond by a recurring wall-clock deadline, while its KV cache grows monotonically and stays pinned for the whole conversation. This regime hides a dangerous failure mode. On a real full-duplex stack, sustained load does not degrade serving gracefully: it falls off a cliff, jumping in one step from milliseconds per frame to a stalled engine when accumulated session state exhausts the KV pool. The collapse is metastable -- identica"},"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":"2607.02640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-02T15:59:01Z","cross_cats_sorted":["cs.AI","cs.NI"],"title_canon_sha256":"9e0ee2e1503ece986ca42c1389ae7c7628a387a8e321f2d8e1e2c9708cefdf30","abstract_canon_sha256":"e7009fac2ef23ff9a3e0c5e03cefcdae1171078becaae86f91bbd1a2eb00fdb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:16:04.867807Z","signature_b64":"qiwwKe01T5js3+Groz+OaxmiUp4DZqOFeUj+HzAskTQpaVCIYSc+TMw6pHJjWLEbpczXCKvV+1aMvkA9ni9oCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"539f98c2b3ee5a4ff310970005bffc0b59e003ccee81563dd2addf58c034d3f4","last_reissued_at":"2026-07-07T00:16:04.867153Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:16:04.867153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.SD","authors_text":"Bojie Li, Jiaying Meng","submitted_at":"2026-07-02T15:59:01Z","abstract_excerpt":"Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming audio and must respond by a recurring wall-clock deadline, while its KV cache grows monotonically and stays pinned for the whole conversation. This regime hides a dangerous failure mode. On a real full-duplex stack, sustained load does not degrade serving gracefully: it falls off a cliff, jumping in one step from milliseconds per frame to a stalled engine when accumulated session state exhausts the KV pool. The collapse is metastable -- identica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02640","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/2607.02640/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":"2607.02640","created_at":"2026-07-07T00:16:04.867260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02640v1","created_at":"2026-07-07T00:16:04.867260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02640","created_at":"2026-07-07T00:16:04.867260+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOPZRQVT5ZNE","created_at":"2026-07-07T00:16:04.867260+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOPZRQVT5ZNE74YQ","created_at":"2026-07-07T00:16:04.867260+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOPZRQVT","created_at":"2026-07-07T00:16:04.867260+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/KOPZRQVT5ZNE74YQS4AALP74BN","json":"https://pith.science/pith/KOPZRQVT5ZNE74YQS4AALP74BN.json","graph_json":"https://pith.science/api/pith-number/KOPZRQVT5ZNE74YQS4AALP74BN/graph.json","events_json":"https://pith.science/api/pith-number/KOPZRQVT5ZNE74YQS4AALP74BN/events.json","paper":"https://pith.science/paper/KOPZRQVT"},"agent_actions":{"view_html":"https://pith.science/pith/KOPZRQVT5ZNE74YQS4AALP74BN","download_json":"https://pith.science/pith/KOPZRQVT5ZNE74YQS4AALP74BN.json","view_paper":"https://pith.science/paper/KOPZRQVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02640&json=true","fetch_graph":"https://pith.science/api/pith-number/KOPZRQVT5ZNE74YQS4AALP74BN/graph.json","fetch_events":"https://pith.science/api/pith-number/KOPZRQVT5ZNE74YQS4AALP74BN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOPZRQVT5ZNE74YQS4AALP74BN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOPZRQVT5ZNE74YQS4AALP74BN/action/storage_attestation","attest_author":"https://pith.science/pith/KOPZRQVT5ZNE74YQS4AALP74BN/action/author_attestation","sign_citation":"https://pith.science/pith/KOPZRQVT5ZNE74YQS4AALP74BN/action/citation_signature","submit_replication":"https://pith.science/pith/KOPZRQVT5ZNE74YQS4AALP74BN/action/replication_record"}},"created_at":"2026-07-07T00:16:04.867260+00:00","updated_at":"2026-07-07T00:16:04.867260+00:00"}