{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PSSB7EWOWKQJU7V3QNJU3XM3C5","short_pith_number":"pith:PSSB7EWO","schema_version":"1.0","canonical_sha256":"7ca41f92ceb2a09a7ebb83534ddd9b175552d0c04a483efbeb47e027b88152c9","source":{"kind":"arxiv","id":"2608.13499","version":1},"attestation_state":"computed","paper":{"title":"OpScale: Operator-level Provisioning and Autoscaling for LLM Serving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chieh-Jan Mike Liang, Haoran Qiu, Jiarong Xing, Xingqi Cui, Ziang Tang","submitted_at":"2026-08-13T17:28:54Z","abstract_excerpt":"Achieving cost efficiency while meeting strict user-facing SLOs (e.g., time-to-first-token) remains a fundamental challenge for cloud GPU clusters serving large language models (LLMs). Autoscaling is the key mechanism for cluster resource management, yet a basic system design question is open for serving LLMs: what should be the unit of scaling? Existing approaches primarily treat the entire model as a monolithic scaling unit--simple but unable to capture the fine-grained dynamics of inference workloads. As a result, such coarse-grained scaling often leads to either SLO violations under bursty"},"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":"2608.13499","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2026-08-13T17:28:54Z","cross_cats_sorted":[],"title_canon_sha256":"40789b420518211e0262a92f140f3d5993b0f7f4a5b0e37adcb541b6ff0b79bc","abstract_canon_sha256":"ee40b5a295d0649dd0059115dd76075c5e4d1e6264181e4fb49b3b01f4f5b22c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:24:53.554234Z","signature_b64":"+MupWZ8nDnMeQIPwEj591F1fQTxS9jo/ycnVgqgLkNEI50g5JbqT+Y4rOmoUHoENGUIrAbHjdMqZY1AWpnA2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ca41f92ceb2a09a7ebb83534ddd9b175552d0c04a483efbeb47e027b88152c9","last_reissued_at":"2026-08-14T01:24:53.551913Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:24:53.551913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpScale: Operator-level Provisioning and Autoscaling for LLM Serving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chieh-Jan Mike Liang, Haoran Qiu, Jiarong Xing, Xingqi Cui, Ziang Tang","submitted_at":"2026-08-13T17:28:54Z","abstract_excerpt":"Achieving cost efficiency while meeting strict user-facing SLOs (e.g., time-to-first-token) remains a fundamental challenge for cloud GPU clusters serving large language models (LLMs). Autoscaling is the key mechanism for cluster resource management, yet a basic system design question is open for serving LLMs: what should be the unit of scaling? Existing approaches primarily treat the entire model as a monolithic scaling unit--simple but unable to capture the fine-grained dynamics of inference workloads. As a result, such coarse-grained scaling often leads to either SLO violations under bursty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13499","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/2608.13499/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":"2608.13499","created_at":"2026-08-14T01:24:53.553492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.13499v1","created_at":"2026-08-14T01:24:53.553492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13499","created_at":"2026-08-14T01:24:53.553492+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSSB7EWOWKQJ","created_at":"2026-08-14T01:24:53.553492+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSSB7EWOWKQJU7V3","created_at":"2026-08-14T01:24:53.553492+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSSB7EWO","created_at":"2026-08-14T01:24:53.553492+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/PSSB7EWOWKQJU7V3QNJU3XM3C5","json":"https://pith.science/pith/PSSB7EWOWKQJU7V3QNJU3XM3C5.json","graph_json":"https://pith.science/api/pith-number/PSSB7EWOWKQJU7V3QNJU3XM3C5/graph.json","events_json":"https://pith.science/api/pith-number/PSSB7EWOWKQJU7V3QNJU3XM3C5/events.json","paper":"https://pith.science/paper/PSSB7EWO"},"agent_actions":{"view_html":"https://pith.science/pith/PSSB7EWOWKQJU7V3QNJU3XM3C5","download_json":"https://pith.science/pith/PSSB7EWOWKQJU7V3QNJU3XM3C5.json","view_paper":"https://pith.science/paper/PSSB7EWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.13499&json=true","fetch_graph":"https://pith.science/api/pith-number/PSSB7EWOWKQJU7V3QNJU3XM3C5/graph.json","fetch_events":"https://pith.science/api/pith-number/PSSB7EWOWKQJU7V3QNJU3XM3C5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSSB7EWOWKQJU7V3QNJU3XM3C5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSSB7EWOWKQJU7V3QNJU3XM3C5/action/storage_attestation","attest_author":"https://pith.science/pith/PSSB7EWOWKQJU7V3QNJU3XM3C5/action/author_attestation","sign_citation":"https://pith.science/pith/PSSB7EWOWKQJU7V3QNJU3XM3C5/action/citation_signature","submit_replication":"https://pith.science/pith/PSSB7EWOWKQJU7V3QNJU3XM3C5/action/replication_record"}},"created_at":"2026-08-14T01:24:53.553492+00:00","updated_at":"2026-08-14T01:24:53.553492+00:00"}