{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C52SEG36NK454NOXFRNNVGI3FJ","short_pith_number":"pith:C52SEG36","schema_version":"1.0","canonical_sha256":"1775221b7e6ab9de35d72c5ada991b2a40e1f1da02ac882c2421431a703d4b5c","source":{"kind":"arxiv","id":"2510.03243","version":3},"attestation_state":"computed","paper":{"title":"Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.PF"],"primary_cat":"cs.LG","authors_text":"Matthew Dearing, Michael E. Papka, Xin Wang, Yiheng Tao, Yihe Zhang, Yuping Fan, Zhiling Lan","submitted_at":"2025-09-25T07:26:38Z","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"},"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":"2510.03243","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T07:26:38Z","cross_cats_sorted":["cs.AI","cs.DC","cs.PF"],"title_canon_sha256":"0521670379ae1154dc5e54448467a48361e8ac8a0f03b79846a74206a9391452","abstract_canon_sha256":"2b16d2875661c7ae4573debb7bd3f509432f7db28bdbe313e4a8271258853e58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:24.652116Z","signature_b64":"uWhT0JU2RjNpYvUBtan64guB+vVtcgYBCVS2aEEbrRhiVKD2My9m2+dxlZY6SZjk7QXPWkUEvzwZvxxsXXUKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1775221b7e6ab9de35d72c5ada991b2a40e1f1da02ac882c2421431a703d4b5c","last_reissued_at":"2026-06-29T01:14:24.651663Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:24.651663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.PF"],"primary_cat":"cs.LG","authors_text":"Matthew Dearing, Michael E. Papka, Xin Wang, Yiheng Tao, Yihe Zhang, Yuping Fan, Zhiling Lan","submitted_at":"2025-09-25T07:26:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03243","kind":"arxiv","version":3},"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/2510.03243/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":"2510.03243","created_at":"2026-06-29T01:14:24.651718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.03243v3","created_at":"2026-06-29T01:14:24.651718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03243","created_at":"2026-06-29T01:14:24.651718+00:00"},{"alias_kind":"pith_short_12","alias_value":"C52SEG36NK45","created_at":"2026-06-29T01:14:24.651718+00:00"},{"alias_kind":"pith_short_16","alias_value":"C52SEG36NK454NOX","created_at":"2026-06-29T01:14:24.651718+00:00"},{"alias_kind":"pith_short_8","alias_value":"C52SEG36","created_at":"2026-06-29T01:14:24.651718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.22327","citing_title":"Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02329","citing_title":"Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02329","citing_title":"Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C52SEG36NK454NOXFRNNVGI3FJ","json":"https://pith.science/pith/C52SEG36NK454NOXFRNNVGI3FJ.json","graph_json":"https://pith.science/api/pith-number/C52SEG36NK454NOXFRNNVGI3FJ/graph.json","events_json":"https://pith.science/api/pith-number/C52SEG36NK454NOXFRNNVGI3FJ/events.json","paper":"https://pith.science/paper/C52SEG36"},"agent_actions":{"view_html":"https://pith.science/pith/C52SEG36NK454NOXFRNNVGI3FJ","download_json":"https://pith.science/pith/C52SEG36NK454NOXFRNNVGI3FJ.json","view_paper":"https://pith.science/paper/C52SEG36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.03243&json=true","fetch_graph":"https://pith.science/api/pith-number/C52SEG36NK454NOXFRNNVGI3FJ/graph.json","fetch_events":"https://pith.science/api/pith-number/C52SEG36NK454NOXFRNNVGI3FJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C52SEG36NK454NOXFRNNVGI3FJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C52SEG36NK454NOXFRNNVGI3FJ/action/storage_attestation","attest_author":"https://pith.science/pith/C52SEG36NK454NOXFRNNVGI3FJ/action/author_attestation","sign_citation":"https://pith.science/pith/C52SEG36NK454NOXFRNNVGI3FJ/action/citation_signature","submit_replication":"https://pith.science/pith/C52SEG36NK454NOXFRNNVGI3FJ/action/replication_record"}},"created_at":"2026-06-29T01:14:24.651718+00:00","updated_at":"2026-06-29T01:14:24.651718+00:00"}