{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C52SEG36NK454NOXFRNNVGI3FJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2b16d2875661c7ae4573debb7bd3f509432f7db28bdbe313e4a8271258853e58","cross_cats_sorted":["cs.AI","cs.DC","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T07:26:38Z","title_canon_sha256":"0521670379ae1154dc5e54448467a48361e8ac8a0f03b79846a74206a9391452"},"schema_version":"1.0","source":{"id":"2510.03243","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.03243","created_at":"2026-06-29T01:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"2510.03243v3","created_at":"2026-06-29T01:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03243","created_at":"2026-06-29T01:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"C52SEG36NK45","created_at":"2026-06-29T01:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"C52SEG36NK454NOX","created_at":"2026-06-29T01:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"C52SEG36","created_at":"2026-06-29T01:14:24Z"}],"graph_snapshots":[{"event_id":"sha256:9855c61e29157d301470ca3562a2db73829935b47adaaff60d1a2d67ece1bfa7","target":"graph","created_at":"2026-06-29T01:14:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.03243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient scheduling of large language model (LLM) inference tasks is critical for achieving low latency and high throughput, a challenge that is becoming increasingly acute with the rise of reasoning-capable LLMs whose generation lengths are highly variable. Traditional strategies like First Come, First-Serve (FCFS) often suffer from Head-of-Line (HOL) blocking, where long-running tasks delay shorter ones queued behind them. In this paper, we introduce PARS, a prompt-aware LLM task scheduler that mitigates HOL blocking by approximating shortest-job-first (SJF) scheduling through pairwise rank","authors_text":"Matthew Dearing, Michael E. Papka, Xin Wang, Yiheng Tao, Yihe Zhang, Yuping Fan, Zhiling Lan","cross_cats":["cs.AI","cs.DC","cs.PF"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T07:26:38Z","title":"Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03243","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ef0b4ef7302295849ce0c9d3fcb0083848f64b11cbb299891060311236240a5f","target":"record","created_at":"2026-06-29T01:14:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2b16d2875661c7ae4573debb7bd3f509432f7db28bdbe313e4a8271258853e58","cross_cats_sorted":["cs.AI","cs.DC","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T07:26:38Z","title_canon_sha256":"0521670379ae1154dc5e54448467a48361e8ac8a0f03b79846a74206a9391452"},"schema_version":"1.0","source":{"id":"2510.03243","kind":"arxiv","version":3}},"canonical_sha256":"1775221b7e6ab9de35d72c5ada991b2a40e1f1da02ac882c2421431a703d4b5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1775221b7e6ab9de35d72c5ada991b2a40e1f1da02ac882c2421431a703d4b5c","first_computed_at":"2026-06-29T01:14:24.651663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:24.651663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uWhT0JU2RjNpYvUBtan64guB+vVtcgYBCVS2aEEbrRhiVKD2My9m2+dxlZY6SZjk7QXPWkUEvzwZvxxsXXUKCw==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:24.652116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.03243","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef0b4ef7302295849ce0c9d3fcb0083848f64b11cbb299891060311236240a5f","sha256:9855c61e29157d301470ca3562a2db73829935b47adaaff60d1a2d67ece1bfa7"],"state_sha256":"d885c5817ec2d13bddd3b2b4fd9022d5d41e09c26560f99cb77792eb09e74a29"}