{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F7AJY4QITLHQSFRIOYIPEU6VVJ","short_pith_number":"pith:F7AJY4QI","schema_version":"1.0","canonical_sha256":"2fc09c72089acf0916287610f253d5aa4cdd3a1195f46ab6280dea28a6add137","source":{"kind":"arxiv","id":"2606.22327","version":1},"attestation_state":"computed","paper":{"title":"Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Li Kong, Qi Qi, Yinyu Ye, Zijie Zhou","submitted_at":"2026-06-21T04:05:38Z","abstract_excerpt":"The explosive demand for interactive Large Language Model serving has highlighted the management of the Key-Value cache's dynamic memory footprint as a critical area for performance optimization in inference engines. Modern inference systems overwhelmingly rely on time-centric scheduling heuristics, such as Shortest Job First. However, their theoretical optimality is rooted in traditional schedule modeling, failing to capture the highly dynamic, 2D spatio-temporal geometric growth specific to LLM inference mechanisms. To resolve this, we propose the geometry-aware online scheduling by introduc"},"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":"2606.22327","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-21T04:05:38Z","cross_cats_sorted":[],"title_canon_sha256":"3b0b3424ef58aa4fe98f8dd2a9dd49ded4db0269e763d7f702825e8f2a7770a4","abstract_canon_sha256":"1a87e66c5c70f5f7d8e3de9e295518821de120848622f5b83f1f422470e6ad2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:34.961821Z","signature_b64":"1eu7cT0uhFjFhN6EeoDKFYN7UcMgJraL5Qf/5PrVEK454+s5tmdPzXroGft1NGcdrwkzpPc9HThIB3iw9vO8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fc09c72089acf0916287610f253d5aa4cdd3a1195f46ab6280dea28a6add137","last_reissued_at":"2026-06-23T02:13:34.961373Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:34.961373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Li Kong, Qi Qi, Yinyu Ye, Zijie Zhou","submitted_at":"2026-06-21T04:05:38Z","abstract_excerpt":"The explosive demand for interactive Large Language Model serving has highlighted the management of the Key-Value cache's dynamic memory footprint as a critical area for performance optimization in inference engines. Modern inference systems overwhelmingly rely on time-centric scheduling heuristics, such as Shortest Job First. However, their theoretical optimality is rooted in traditional schedule modeling, failing to capture the highly dynamic, 2D spatio-temporal geometric growth specific to LLM inference mechanisms. To resolve this, we propose the geometry-aware online scheduling by introduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22327","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/2606.22327/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":"2606.22327","created_at":"2026-06-23T02:13:34.961438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22327v1","created_at":"2026-06-23T02:13:34.961438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22327","created_at":"2026-06-23T02:13:34.961438+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7AJY4QITLHQ","created_at":"2026-06-23T02:13:34.961438+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7AJY4QITLHQSFRI","created_at":"2026-06-23T02:13:34.961438+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7AJY4QI","created_at":"2026-06-23T02:13:34.961438+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/F7AJY4QITLHQSFRIOYIPEU6VVJ","json":"https://pith.science/pith/F7AJY4QITLHQSFRIOYIPEU6VVJ.json","graph_json":"https://pith.science/api/pith-number/F7AJY4QITLHQSFRIOYIPEU6VVJ/graph.json","events_json":"https://pith.science/api/pith-number/F7AJY4QITLHQSFRIOYIPEU6VVJ/events.json","paper":"https://pith.science/paper/F7AJY4QI"},"agent_actions":{"view_html":"https://pith.science/pith/F7AJY4QITLHQSFRIOYIPEU6VVJ","download_json":"https://pith.science/pith/F7AJY4QITLHQSFRIOYIPEU6VVJ.json","view_paper":"https://pith.science/paper/F7AJY4QI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22327&json=true","fetch_graph":"https://pith.science/api/pith-number/F7AJY4QITLHQSFRIOYIPEU6VVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/F7AJY4QITLHQSFRIOYIPEU6VVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7AJY4QITLHQSFRIOYIPEU6VVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7AJY4QITLHQSFRIOYIPEU6VVJ/action/storage_attestation","attest_author":"https://pith.science/pith/F7AJY4QITLHQSFRIOYIPEU6VVJ/action/author_attestation","sign_citation":"https://pith.science/pith/F7AJY4QITLHQSFRIOYIPEU6VVJ/action/citation_signature","submit_replication":"https://pith.science/pith/F7AJY4QITLHQSFRIOYIPEU6VVJ/action/replication_record"}},"created_at":"2026-06-23T02:13:34.961438+00:00","updated_at":"2026-06-23T02:13:34.961438+00:00"}