{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D6S2FLXNQ77V7KSSZ5XNTCPWJD","short_pith_number":"pith:D6S2FLXN","schema_version":"1.0","canonical_sha256":"1fa5a2aeed87ff5faa52cf6ed989f648e32cc67dd30322d37cbed059534574e1","source":{"kind":"arxiv","id":"2606.05933","version":1},"attestation_state":"computed","paper":{"title":"Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Jialun Li, Weigang Wu, Xuan Mo, Yuansheng Chen, Yue Zhang","submitted_at":"2026-06-04T09:36:40Z","abstract_excerpt":"With the rapid growth of interactive applications in large language model (LLM) online services, maintaining high system throughput while ensuring user-perceived latency has become a key issue in inference scheduling. Existing LLM service systems rely on coarse-grained output constraints, making it difficult to effectively handle resource contention among multiple requests, resulting in low resource utilization efficiency and limited support for fine-grained quality of service (QoS) differentiation. We present SlidingServe, a sliding-window-driven SLO-Aware scheduling system for online LLM inf"},"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":"2606.05933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-04T09:36:40Z","cross_cats_sorted":[],"title_canon_sha256":"d0a9d9fea93b78a48d19e19ae70866a5fcaf1fe2e6af92ae1aa7da7ac585e479","abstract_canon_sha256":"6f81c7a85c570180273914d3399ed5beda6f9a922e160f97d1cbc1fa8d4f3c1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:28.128925Z","signature_b64":"A1tDl9R1xSldHyb6PjMB9H0Ecj6C7Vr+suzw96zDuFfKILl005SZeEin0tLADol0KItyy3SNEcsklhMqbNfwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fa5a2aeed87ff5faa52cf6ed989f648e32cc67dd30322d37cbed059534574e1","last_reissued_at":"2026-06-05T01:15:28.128509Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:28.128509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Jialun Li, Weigang Wu, Xuan Mo, Yuansheng Chen, Yue Zhang","submitted_at":"2026-06-04T09:36:40Z","abstract_excerpt":"With the rapid growth of interactive applications in large language model (LLM) online services, maintaining high system throughput while ensuring user-perceived latency has become a key issue in inference scheduling. Existing LLM service systems rely on coarse-grained output constraints, making it difficult to effectively handle resource contention among multiple requests, resulting in low resource utilization efficiency and limited support for fine-grained quality of service (QoS) differentiation. We present SlidingServe, a sliding-window-driven SLO-Aware scheduling system for online LLM inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05933","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/2606.05933/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":"2606.05933","created_at":"2026-06-05T01:15:28.128570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05933v1","created_at":"2026-06-05T01:15:28.128570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05933","created_at":"2026-06-05T01:15:28.128570+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6S2FLXNQ77V","created_at":"2026-06-05T01:15:28.128570+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6S2FLXNQ77V7KSS","created_at":"2026-06-05T01:15:28.128570+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6S2FLXN","created_at":"2026-06-05T01:15:28.128570+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/D6S2FLXNQ77V7KSSZ5XNTCPWJD","json":"https://pith.science/pith/D6S2FLXNQ77V7KSSZ5XNTCPWJD.json","graph_json":"https://pith.science/api/pith-number/D6S2FLXNQ77V7KSSZ5XNTCPWJD/graph.json","events_json":"https://pith.science/api/pith-number/D6S2FLXNQ77V7KSSZ5XNTCPWJD/events.json","paper":"https://pith.science/paper/D6S2FLXN"},"agent_actions":{"view_html":"https://pith.science/pith/D6S2FLXNQ77V7KSSZ5XNTCPWJD","download_json":"https://pith.science/pith/D6S2FLXNQ77V7KSSZ5XNTCPWJD.json","view_paper":"https://pith.science/paper/D6S2FLXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05933&json=true","fetch_graph":"https://pith.science/api/pith-number/D6S2FLXNQ77V7KSSZ5XNTCPWJD/graph.json","fetch_events":"https://pith.science/api/pith-number/D6S2FLXNQ77V7KSSZ5XNTCPWJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6S2FLXNQ77V7KSSZ5XNTCPWJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6S2FLXNQ77V7KSSZ5XNTCPWJD/action/storage_attestation","attest_author":"https://pith.science/pith/D6S2FLXNQ77V7KSSZ5XNTCPWJD/action/author_attestation","sign_citation":"https://pith.science/pith/D6S2FLXNQ77V7KSSZ5XNTCPWJD/action/citation_signature","submit_replication":"https://pith.science/pith/D6S2FLXNQ77V7KSSZ5XNTCPWJD/action/replication_record"}},"created_at":"2026-06-05T01:15:28.128570+00:00","updated_at":"2026-06-05T01:15:28.128570+00:00"}