{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CRPQAYB2OMHUQEM5XKUL3NHJPU","short_pith_number":"pith:CRPQAYB2","schema_version":"1.0","canonical_sha256":"145f00603a730f48119dbaa8bdb4e97d32f728fbc8ea256714af21da03e89b5b","source":{"kind":"arxiv","id":"2602.11688","version":2},"attestation_state":"computed","paper":{"title":"GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.NI","authors_text":"Abinaya Dinesh, Alessio Ricci Toniolo, Rome Thorstenson","submitted_at":"2026-02-12T08:09:14Z","abstract_excerpt":"Increasingly, LLM inference services proxy client requests to engine replicas distributed globally. Load-balancing policies must jointly account for factors including KV-cache locality, replica load, and variable network latency when optimizing for metrics like latency and TTFT. However, existing systems only evaluate a subset of these factors in their cost model, leading to uneven concentrations of load and KV-cache across replicas. We present GORGO, a proxy architecture that holistically factors network latency, prefill cost, and queueing delay using tunable parameters. Since open-source cha"},"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":"2602.11688","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2026-02-12T08:09:14Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"44aa716d7d47279527a5ad52bb4a8f2fe22ffde139415bba26e069f52b7a5f60","abstract_canon_sha256":"06bde175c383970146f8a6dee2c6b7946ae239a98c71ec76e4fc2bef7f070272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:13.476092Z","signature_b64":"yMKXHPQV7mimRGyJ8MGoullcPCNaiTg3EZTI2iwu5K7ja2fjfIR7eisMrZv9p/fYbMst9vlyR/Xb29EXORKtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"145f00603a730f48119dbaa8bdb4e97d32f728fbc8ea256714af21da03e89b5b","last_reissued_at":"2026-07-01T01:17:13.475488Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:13.475488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.NI","authors_text":"Abinaya Dinesh, Alessio Ricci Toniolo, Rome Thorstenson","submitted_at":"2026-02-12T08:09:14Z","abstract_excerpt":"Increasingly, LLM inference services proxy client requests to engine replicas distributed globally. Load-balancing policies must jointly account for factors including KV-cache locality, replica load, and variable network latency when optimizing for metrics like latency and TTFT. However, existing systems only evaluate a subset of these factors in their cost model, leading to uneven concentrations of load and KV-cache across replicas. We present GORGO, a proxy architecture that holistically factors network latency, prefill cost, and queueing delay using tunable parameters. Since open-source cha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11688","kind":"arxiv","version":2},"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/2602.11688/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":"2602.11688","created_at":"2026-07-01T01:17:13.475553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11688v2","created_at":"2026-07-01T01:17:13.475553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11688","created_at":"2026-07-01T01:17:13.475553+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRPQAYB2OMHU","created_at":"2026-07-01T01:17:13.475553+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRPQAYB2OMHUQEM5","created_at":"2026-07-01T01:17:13.475553+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRPQAYB2","created_at":"2026-07-01T01:17:13.475553+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/CRPQAYB2OMHUQEM5XKUL3NHJPU","json":"https://pith.science/pith/CRPQAYB2OMHUQEM5XKUL3NHJPU.json","graph_json":"https://pith.science/api/pith-number/CRPQAYB2OMHUQEM5XKUL3NHJPU/graph.json","events_json":"https://pith.science/api/pith-number/CRPQAYB2OMHUQEM5XKUL3NHJPU/events.json","paper":"https://pith.science/paper/CRPQAYB2"},"agent_actions":{"view_html":"https://pith.science/pith/CRPQAYB2OMHUQEM5XKUL3NHJPU","download_json":"https://pith.science/pith/CRPQAYB2OMHUQEM5XKUL3NHJPU.json","view_paper":"https://pith.science/paper/CRPQAYB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11688&json=true","fetch_graph":"https://pith.science/api/pith-number/CRPQAYB2OMHUQEM5XKUL3NHJPU/graph.json","fetch_events":"https://pith.science/api/pith-number/CRPQAYB2OMHUQEM5XKUL3NHJPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRPQAYB2OMHUQEM5XKUL3NHJPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRPQAYB2OMHUQEM5XKUL3NHJPU/action/storage_attestation","attest_author":"https://pith.science/pith/CRPQAYB2OMHUQEM5XKUL3NHJPU/action/author_attestation","sign_citation":"https://pith.science/pith/CRPQAYB2OMHUQEM5XKUL3NHJPU/action/citation_signature","submit_replication":"https://pith.science/pith/CRPQAYB2OMHUQEM5XKUL3NHJPU/action/replication_record"}},"created_at":"2026-07-01T01:17:13.475553+00:00","updated_at":"2026-07-01T01:17:13.475553+00:00"}