{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IOAIZMQW5QYG5DON64ZO5EMRP6","short_pith_number":"pith:IOAIZMQW","schema_version":"1.0","canonical_sha256":"43808cb216ec306e8dcdf732ee91917fb565a8a7d1b92aaa189a5b8eb4125f27","source":{"kind":"arxiv","id":"2606.17949","version":1},"attestation_state":"computed","paper":{"title":"RouteBalance: Fused Model Routing and Load Balancing for Heterogeneous LLM Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Evangelia Kalyvianaki, Wei Da","submitted_at":"2026-06-16T14:02:34Z","abstract_excerpt":"Heterogeneous LLM serving stacks split scheduling into two layers that optimize in isolation: model routers pick a model from quality and cost signals while ignoring instance load, and serving load balancers optimize queues while ignoring quality. We present RouteBalance, a serving-aware scheduling layer that fuses both into a single online assignment over concrete model instances, jointly trading off quality, latency, and cost. A batched in-process predictor stack and dead-reckoned instance state keep the joint decision cheap on the request hot path ($\\approx$32 ms at 12 req/s). On a 13-insta"},"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":"2606.17949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-16T14:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"bf1af85a692642e400b21f38fa200e92675da516f80ced4fb07756698b57cc78","abstract_canon_sha256":"8275f93eb0c8062d0b50e1c351de1bb1d63517a27fcac44d38a58f2b14da8c13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:44.310431Z","signature_b64":"Zl8xXlhB9ziAO61EkUyaBFQPQXbN3kANWeo7YFQWOjhRbr43/3dzAGWc9cVpoN/xp6UiSZV5y972z6LNmSSRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43808cb216ec306e8dcdf732ee91917fb565a8a7d1b92aaa189a5b8eb4125f27","last_reissued_at":"2026-06-19T16:10:44.310069Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:44.310069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RouteBalance: Fused Model Routing and Load Balancing for Heterogeneous LLM Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Evangelia Kalyvianaki, Wei Da","submitted_at":"2026-06-16T14:02:34Z","abstract_excerpt":"Heterogeneous LLM serving stacks split scheduling into two layers that optimize in isolation: model routers pick a model from quality and cost signals while ignoring instance load, and serving load balancers optimize queues while ignoring quality. We present RouteBalance, a serving-aware scheduling layer that fuses both into a single online assignment over concrete model instances, jointly trading off quality, latency, and cost. A batched in-process predictor stack and dead-reckoned instance state keep the joint decision cheap on the request hot path ($\\approx$32 ms at 12 req/s). On a 13-insta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17949","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/2606.17949/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":"2606.17949","created_at":"2026-06-19T16:10:44.310131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17949v1","created_at":"2026-06-19T16:10:44.310131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17949","created_at":"2026-06-19T16:10:44.310131+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOAIZMQW5QYG","created_at":"2026-06-19T16:10:44.310131+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOAIZMQW5QYG5DON","created_at":"2026-06-19T16:10:44.310131+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOAIZMQW","created_at":"2026-06-19T16:10:44.310131+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/IOAIZMQW5QYG5DON64ZO5EMRP6","json":"https://pith.science/pith/IOAIZMQW5QYG5DON64ZO5EMRP6.json","graph_json":"https://pith.science/api/pith-number/IOAIZMQW5QYG5DON64ZO5EMRP6/graph.json","events_json":"https://pith.science/api/pith-number/IOAIZMQW5QYG5DON64ZO5EMRP6/events.json","paper":"https://pith.science/paper/IOAIZMQW"},"agent_actions":{"view_html":"https://pith.science/pith/IOAIZMQW5QYG5DON64ZO5EMRP6","download_json":"https://pith.science/pith/IOAIZMQW5QYG5DON64ZO5EMRP6.json","view_paper":"https://pith.science/paper/IOAIZMQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17949&json=true","fetch_graph":"https://pith.science/api/pith-number/IOAIZMQW5QYG5DON64ZO5EMRP6/graph.json","fetch_events":"https://pith.science/api/pith-number/IOAIZMQW5QYG5DON64ZO5EMRP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOAIZMQW5QYG5DON64ZO5EMRP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOAIZMQW5QYG5DON64ZO5EMRP6/action/storage_attestation","attest_author":"https://pith.science/pith/IOAIZMQW5QYG5DON64ZO5EMRP6/action/author_attestation","sign_citation":"https://pith.science/pith/IOAIZMQW5QYG5DON64ZO5EMRP6/action/citation_signature","submit_replication":"https://pith.science/pith/IOAIZMQW5QYG5DON64ZO5EMRP6/action/replication_record"}},"created_at":"2026-06-19T16:10:44.310131+00:00","updated_at":"2026-06-19T16:10:44.310131+00:00"}