{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DPAEFPU3TBO6J6CR36PPRWP6C6","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":"6aa6352217b778e6cb66cb21e0e7a3d4f380abccb1e32413fb2f92853b5c0a59","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T19:25:37Z","title_canon_sha256":"78928151ce54a97aa5d681940077813751ac5a526d501ed196d0cedbe130d14d"},"schema_version":"1.0","source":{"id":"2606.18431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18431","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18431v1","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18431","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"pith_short_12","alias_value":"DPAEFPU3TBO6","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"pith_short_16","alias_value":"DPAEFPU3TBO6J6CR","created_at":"2026-06-19T16:11:01Z"},{"alias_kind":"pith_short_8","alias_value":"DPAEFPU3","created_at":"2026-06-19T16:11:01Z"}],"graph_snapshots":[{"event_id":"sha256:20df8a682275c8cc1b068feddef856ebb1c1a4feea2c967d6d608ddb1871c472","target":"graph","created_at":"2026-06-19T16:11:01Z","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/2606.18431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM serving exhibits extreme length variability, making size-based scheduling difficult in practice. Recent LLM schedulers approximate SJF/SRPT using predicted decode lengths or ranks and primarily report mean-centric metrics such as TTFT and TBT. We show that these prediction-driven policies can be fragile under distribution shifts, bursty arrivals, and GPU memory pressure, while offering limited control over the tail latency (P90-P99) that dominates user experience, even with perfect decode-length knowledge. We introduce a distribution-aware, prediction-free scheduling framework that replace","authors_text":"Esha Choukse, G. Edward Suh, Haoran Qiu, Jiayang Chen, Rodrigo Fonseca, Udit Gupta, Yuanfan Chen, Yueying Li, Ziv Scully","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T19:25:37Z","title":"Beyond Prediction: Tail-Aware Scheduling for LLM Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18431","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":"sha256:5b4ed99b9c57e246613a6e160bbdfacd4eab4edb08afec6b282b204c9445084f","target":"record","created_at":"2026-06-19T16:11:01Z","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":"6aa6352217b778e6cb66cb21e0e7a3d4f380abccb1e32413fb2f92853b5c0a59","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T19:25:37Z","title_canon_sha256":"78928151ce54a97aa5d681940077813751ac5a526d501ed196d0cedbe130d14d"},"schema_version":"1.0","source":{"id":"2606.18431","kind":"arxiv","version":1}},"canonical_sha256":"1bc042be9b985de4f851df9ef8d9fe17b22b49e02dc69da7fe786bad22f63c1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bc042be9b985de4f851df9ef8d9fe17b22b49e02dc69da7fe786bad22f63c1b","first_computed_at":"2026-06-19T16:11:01.084092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:01.084092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ACIFiLswUQdPDwNIg7ShrCEzYbBMJL+B+R0FgSkej2WRDISrQ7PF8PMP/wKEPEXJj5AwqY2LEw+ofx6dQ2naDA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:01.084444Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b4ed99b9c57e246613a6e160bbdfacd4eab4edb08afec6b282b204c9445084f","sha256:20df8a682275c8cc1b068feddef856ebb1c1a4feea2c967d6d608ddb1871c472"],"state_sha256":"d8b9db72fe3e9e926c13d8e9780bd224a1cf7f6414fb78770bb2866e81b72514"}