{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S4DUECI43RVMNMP3B6X7AVN3WS","short_pith_number":"pith:S4DUECI4","schema_version":"1.0","canonical_sha256":"970742091cdc6ac6b1fb0faff055bbb4a57d4b96b410048f2ae850d952d19c84","source":{"kind":"arxiv","id":"2508.14544","version":2},"attestation_state":"computed","paper":{"title":"Adaptively Robust LLM Inference Optimization under Prediction Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Yinyu Ye, Zijie Zhou, Zixi Chen","submitted_at":"2025-08-20T08:55:26Z","abstract_excerpt":"We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes input requests and generates output tokens sequentially. Therefore, it is vital to improve its scheduling efficiency and reduce the power consumption while a great amount of prompt requests are arriving. A key challenge in LLM inference scheduling is that while the prompt length is known upon arrival, the output length, which critically impacts memory usage a"},"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":"2508.14544","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T08:55:26Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"f1f3dc6f52b31b193f8ccf2af5135b0278459e7d44fb6050c227a8fe904f97b2","abstract_canon_sha256":"b32e3ba5e3d1550bead12e5ea0189c46b2bd43f5017f00a758d1092723af7f99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:50.488702Z","signature_b64":"b+D78jZDhVgVxs7dgozG18A3vljF/xOR7tPERYaBf3ihsJG1q79JgBTyPTOWbkpokbsqrewwi6ZRA4XFSxHBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"970742091cdc6ac6b1fb0faff055bbb4a57d4b96b410048f2ae850d952d19c84","last_reissued_at":"2026-07-05T12:02:50.488204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:50.488204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptively Robust LLM Inference Optimization under Prediction Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Yinyu Ye, Zijie Zhou, Zixi Chen","submitted_at":"2025-08-20T08:55:26Z","abstract_excerpt":"We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes input requests and generates output tokens sequentially. Therefore, it is vital to improve its scheduling efficiency and reduce the power consumption while a great amount of prompt requests are arriving. A key challenge in LLM inference scheduling is that while the prompt length is known upon arrival, the output length, which critically impacts memory usage a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14544","kind":"arxiv","version":2},"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/2508.14544/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":"2508.14544","created_at":"2026-07-05T12:02:50.488263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14544v2","created_at":"2026-07-05T12:02:50.488263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14544","created_at":"2026-07-05T12:02:50.488263+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4DUECI43RVM","created_at":"2026-07-05T12:02:50.488263+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4DUECI43RVMNMP3","created_at":"2026-07-05T12:02:50.488263+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4DUECI4","created_at":"2026-07-05T12:02:50.488263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22327","citing_title":"Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2504.11320","citing_title":"Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06113","citing_title":"Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04595","citing_title":"A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01280","citing_title":"Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11001","citing_title":"Flow-Controlled Scheduling for LLM Inference with Provable Stability Guarantees","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06113","citing_title":"Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4DUECI43RVMNMP3B6X7AVN3WS","json":"https://pith.science/pith/S4DUECI43RVMNMP3B6X7AVN3WS.json","graph_json":"https://pith.science/api/pith-number/S4DUECI43RVMNMP3B6X7AVN3WS/graph.json","events_json":"https://pith.science/api/pith-number/S4DUECI43RVMNMP3B6X7AVN3WS/events.json","paper":"https://pith.science/paper/S4DUECI4"},"agent_actions":{"view_html":"https://pith.science/pith/S4DUECI43RVMNMP3B6X7AVN3WS","download_json":"https://pith.science/pith/S4DUECI43RVMNMP3B6X7AVN3WS.json","view_paper":"https://pith.science/paper/S4DUECI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14544&json=true","fetch_graph":"https://pith.science/api/pith-number/S4DUECI43RVMNMP3B6X7AVN3WS/graph.json","fetch_events":"https://pith.science/api/pith-number/S4DUECI43RVMNMP3B6X7AVN3WS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4DUECI43RVMNMP3B6X7AVN3WS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4DUECI43RVMNMP3B6X7AVN3WS/action/storage_attestation","attest_author":"https://pith.science/pith/S4DUECI43RVMNMP3B6X7AVN3WS/action/author_attestation","sign_citation":"https://pith.science/pith/S4DUECI43RVMNMP3B6X7AVN3WS/action/citation_signature","submit_replication":"https://pith.science/pith/S4DUECI43RVMNMP3B6X7AVN3WS/action/replication_record"}},"created_at":"2026-07-05T12:02:50.488263+00:00","updated_at":"2026-07-05T12:02:50.488263+00:00"}