{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IPJOALITFO363UOPAO7KWW2VOO","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":"83ec0f2aa5b39e72760c494fb54466a9848444a41a35753f1dfa29f834a630dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-28T13:35:54Z","title_canon_sha256":"3a57e154c9304648baedc2dd2b3a2d8fdabaf9a9b9044816d1ef823429497bca"},"schema_version":"1.0","source":{"id":"2408.15792","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15792","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15792v1","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15792","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"pith_short_12","alias_value":"IPJOALITFO36","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"pith_short_16","alias_value":"IPJOALITFO363UOP","created_at":"2026-07-05T09:00:17Z"},{"alias_kind":"pith_short_8","alias_value":"IPJOALIT","created_at":"2026-07-05T09:00:17Z"}],"graph_snapshots":[{"event_id":"sha256:99b97d659205c2ef23e59e599cba604420108e98e37bbbf52b170bf639e62e57","target":"graph","created_at":"2026-07-05T09:00:17Z","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/2408.15792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to Head-Of-Line (HOL) blocking and reduced throughput and service quality. In this paper, we reexamine this assumption -- we show that, although predicting the exact generation length of each request is infeasible, it is possible to predict the relative ranks of output lengths in a batch of requests, using learning to rank. The ranking information offers valuabl","authors_text":"Aurick Qiao, Hao Zhang, Ion Stoica, Runlong Su, Siqi Zhu, Yichao Fu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-28T13:35:54Z","title":"Efficient LLM Scheduling by Learning to Rank"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15792","kind":"arxiv","version":1},"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":"sha256:5efa529f5c0fe8b5334c1f8e8c5d4f3e2faf05136b5f57605a5102b407903c7e","target":"record","created_at":"2026-07-05T09:00:17Z","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":"83ec0f2aa5b39e72760c494fb54466a9848444a41a35753f1dfa29f834a630dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-28T13:35:54Z","title_canon_sha256":"3a57e154c9304648baedc2dd2b3a2d8fdabaf9a9b9044816d1ef823429497bca"},"schema_version":"1.0","source":{"id":"2408.15792","kind":"arxiv","version":1}},"canonical_sha256":"43d2e02d132bb7edd1cf03beab5b5573924a814430867296749b8a90e765d5c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43d2e02d132bb7edd1cf03beab5b5573924a814430867296749b8a90e765d5c9","first_computed_at":"2026-07-05T09:00:17.567506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:17.567506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sFoaz5lpCXsstE7L2BaICS1bzTZ7E8FhQbw/07fs8b+cf8QHn3Oy64GMfVJsRqhh9KqPlAHSXgJRZe+EtOUzAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:17.568018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15792","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5efa529f5c0fe8b5334c1f8e8c5d4f3e2faf05136b5f57605a5102b407903c7e","sha256:99b97d659205c2ef23e59e599cba604420108e98e37bbbf52b170bf639e62e57"],"state_sha256":"6e02681e63184c8467783ba3a1011e5292259c56122fef743186345e1ef748e3"}