{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7VRENOHDZF7O2F6H26FGQNAYZN","short_pith_number":"pith:7VRENOHD","schema_version":"1.0","canonical_sha256":"fd6246b8e3c97eed17c7d78a683418cb563d05c742cf72f9ef9617a6ee80c002","source":{"kind":"arxiv","id":"2606.07248","version":1},"attestation_state":"computed","paper":{"title":"Clairvoyant: Predictive SJF Scheduling to Mitigate Head-of-Line Blocking in Serial LLM Backends","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Aravind Sundaresan","submitted_at":"2026-06-05T13:19:05Z","abstract_excerpt":"Serial LLM inference backends -- such as Ollama -- process requests one at a time under FCFS admission, causing Head-of-Line Blocking (HOLB) under mixed workloads at high utilisation: short factual queries can be delayed by minutes behind long generation jobs. While cloud-scale deployments mitigate HOLB via continuous batching (vLLM, Orca), these solutions require tens of GB of VRAM for concurrent KV-caches -- infeasible for memory-constrained edge and local deployments that rely on serial request dispatch. We present \\clairvoyant, a drop-in sidecar proxy for any serial OpenAI-compatible backe"},"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":"2606.07248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-05T13:19:05Z","cross_cats_sorted":[],"title_canon_sha256":"d73c145c093f66d109fc4cae266d93875a53f1fb788ab120855eae1cf8a79f20","abstract_canon_sha256":"098c240ffaea8b53eac0de9879e69cafa88576c73198af36e0eddda348d10860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:15.523801Z","signature_b64":"B0WpkeR10OQ5dxwj3R0eltgj+OjdJXQvuqxGcj0J94ybYdKhuoV/vDtoxJl05JeHylEq7xKGZNHcCAMKvdCCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd6246b8e3c97eed17c7d78a683418cb563d05c742cf72f9ef9617a6ee80c002","last_reissued_at":"2026-06-08T01:05:15.523017Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:15.523017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clairvoyant: Predictive SJF Scheduling to Mitigate Head-of-Line Blocking in Serial LLM Backends","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Aravind Sundaresan","submitted_at":"2026-06-05T13:19:05Z","abstract_excerpt":"Serial LLM inference backends -- such as Ollama -- process requests one at a time under FCFS admission, causing Head-of-Line Blocking (HOLB) under mixed workloads at high utilisation: short factual queries can be delayed by minutes behind long generation jobs. While cloud-scale deployments mitigate HOLB via continuous batching (vLLM, Orca), these solutions require tens of GB of VRAM for concurrent KV-caches -- infeasible for memory-constrained edge and local deployments that rely on serial request dispatch. We present \\clairvoyant, a drop-in sidecar proxy for any serial OpenAI-compatible backe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07248","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/2606.07248/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":"2606.07248","created_at":"2026-06-08T01:05:15.523145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07248v1","created_at":"2026-06-08T01:05:15.523145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07248","created_at":"2026-06-08T01:05:15.523145+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VRENOHDZF7O","created_at":"2026-06-08T01:05:15.523145+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VRENOHDZF7O2F6H","created_at":"2026-06-08T01:05:15.523145+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VRENOHD","created_at":"2026-06-08T01:05:15.523145+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/7VRENOHDZF7O2F6H26FGQNAYZN","json":"https://pith.science/pith/7VRENOHDZF7O2F6H26FGQNAYZN.json","graph_json":"https://pith.science/api/pith-number/7VRENOHDZF7O2F6H26FGQNAYZN/graph.json","events_json":"https://pith.science/api/pith-number/7VRENOHDZF7O2F6H26FGQNAYZN/events.json","paper":"https://pith.science/paper/7VRENOHD"},"agent_actions":{"view_html":"https://pith.science/pith/7VRENOHDZF7O2F6H26FGQNAYZN","download_json":"https://pith.science/pith/7VRENOHDZF7O2F6H26FGQNAYZN.json","view_paper":"https://pith.science/paper/7VRENOHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07248&json=true","fetch_graph":"https://pith.science/api/pith-number/7VRENOHDZF7O2F6H26FGQNAYZN/graph.json","fetch_events":"https://pith.science/api/pith-number/7VRENOHDZF7O2F6H26FGQNAYZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VRENOHDZF7O2F6H26FGQNAYZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VRENOHDZF7O2F6H26FGQNAYZN/action/storage_attestation","attest_author":"https://pith.science/pith/7VRENOHDZF7O2F6H26FGQNAYZN/action/author_attestation","sign_citation":"https://pith.science/pith/7VRENOHDZF7O2F6H26FGQNAYZN/action/citation_signature","submit_replication":"https://pith.science/pith/7VRENOHDZF7O2F6H26FGQNAYZN/action/replication_record"}},"created_at":"2026-06-08T01:05:15.523145+00:00","updated_at":"2026-06-08T01:05:15.523145+00:00"}