{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4OWXBMWVOB5S5R7MCUVSJNUQGB","short_pith_number":"pith:4OWXBMWV","canonical_record":{"source":{"id":"2501.14312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T08:12:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"86f108b3c409acf7b20b98bfd5c788f59d4a43e3e5a6e13cd805c227a68e938e","abstract_canon_sha256":"ca605e54e380ad31b29faca760cbc0914c6a0385f6c517bf9e5c9f7913975afc"},"schema_version":"1.0"},"canonical_sha256":"e3ad70b2d5707b2ec7ec152b24b69030712f196c821fed16bafdba429c01c2c6","source":{"kind":"arxiv","id":"2501.14312","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14312","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14312v1","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14312","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"4OWXBMWVOB5S","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"4OWXBMWVOB5S5R7M","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"4OWXBMWV","created_at":"2026-07-05T10:04:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4OWXBMWVOB5S5R7MCUVSJNUQGB","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T08:12:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"86f108b3c409acf7b20b98bfd5c788f59d4a43e3e5a6e13cd805c227a68e938e","abstract_canon_sha256":"ca605e54e380ad31b29faca760cbc0914c6a0385f6c517bf9e5c9f7913975afc"},"schema_version":"1.0"},"canonical_sha256":"e3ad70b2d5707b2ec7ec152b24b69030712f196c821fed16bafdba429c01c2c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:48.651164Z","signature_b64":"5tE3BOOZ5I9edWJlVtOimCJCFXStpamSq7X1TkfUXplOEA4QZxaL7UmiWPdtAH9CDEzr2r5pqUqKMDhsPp0FBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3ad70b2d5707b2ec7ec152b24b69030712f196c821fed16bafdba429c01c2c6","last_reissued_at":"2026-07-05T10:04:48.650606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:48.650606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14312","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JUXfXo2hOnpCRMJysRTqwVNy4ceEi3UkgMJSWFLA0SrQaBnsRoJGGScddDArLd+YqQrRHnuy5FcebqXit/qxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:59:34.660139Z"},"content_sha256":"cf63157891cd5ce2cb4f9b5662d6dce16293979c8756f7b3080ff5fe3966d8a9","schema_version":"1.0","event_id":"sha256:cf63157891cd5ce2cb4f9b5662d6dce16293979c8756f7b3080ff5fe3966d8a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4OWXBMWVOB5S5R7MCUVSJNUQGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Locality-aware Fair Scheduling in LLM Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Dacheng Li, Ion Stoica, Joseph Gonzalez, Liangsheng Yin, Pin-Lun Hsu, Shiyi Cao, Shu Liu, Tian Xia, Yang Zhou, Yichuan Wang, Yineng Zhang, Ying Sheng, Ziming Mao","submitted_at":"2025-01-24T08:12:47Z","abstract_excerpt":"Large language model (LLM) inference workload dominates a wide variety of modern AI applications, ranging from multi-turn conversation to document analysis. Balancing fairness and efficiency is critical for managing diverse client workloads with varying prefix patterns. Unfortunately, existing fair scheduling algorithms for LLM serving, such as Virtual Token Counter (VTC), fail to take prefix locality into consideration and thus suffer from poor performance. On the other hand, locality-aware scheduling algorithms in existing LLM serving frameworks tend to maximize the prefix cache hit rate wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14312","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/2501.14312/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6RRHn8kAcrWTdBUcbvXFDobFTHiGjMKvyQaeK1ESM6PL+ZkhWCcWEHW5hhkXQdoEgbkgJVbksKw389UOrtWGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:59:34.660753Z"},"content_sha256":"85b0a4153788f46f20d9fcae53d27a71b19698c28196826c65cc1b317b371556","schema_version":"1.0","event_id":"sha256:85b0a4153788f46f20d9fcae53d27a71b19698c28196826c65cc1b317b371556"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OWXBMWVOB5S5R7MCUVSJNUQGB/bundle.json","state_url":"https://pith.science/pith/4OWXBMWVOB5S5R7MCUVSJNUQGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OWXBMWVOB5S5R7MCUVSJNUQGB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T13:59:34Z","links":{"resolver":"https://pith.science/pith/4OWXBMWVOB5S5R7MCUVSJNUQGB","bundle":"https://pith.science/pith/4OWXBMWVOB5S5R7MCUVSJNUQGB/bundle.json","state":"https://pith.science/pith/4OWXBMWVOB5S5R7MCUVSJNUQGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OWXBMWVOB5S5R7MCUVSJNUQGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4OWXBMWVOB5S5R7MCUVSJNUQGB","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":"ca605e54e380ad31b29faca760cbc0914c6a0385f6c517bf9e5c9f7913975afc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T08:12:47Z","title_canon_sha256":"86f108b3c409acf7b20b98bfd5c788f59d4a43e3e5a6e13cd805c227a68e938e"},"schema_version":"1.0","source":{"id":"2501.14312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14312","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14312v1","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14312","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"4OWXBMWVOB5S","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"4OWXBMWVOB5S5R7M","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"4OWXBMWV","created_at":"2026-07-05T10:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:85b0a4153788f46f20d9fcae53d27a71b19698c28196826c65cc1b317b371556","target":"graph","created_at":"2026-07-05T10:04:48Z","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/2501.14312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) inference workload dominates a wide variety of modern AI applications, ranging from multi-turn conversation to document analysis. Balancing fairness and efficiency is critical for managing diverse client workloads with varying prefix patterns. Unfortunately, existing fair scheduling algorithms for LLM serving, such as Virtual Token Counter (VTC), fail to take prefix locality into consideration and thus suffer from poor performance. On the other hand, locality-aware scheduling algorithms in existing LLM serving frameworks tend to maximize the prefix cache hit rate wit","authors_text":"Dacheng Li, Ion Stoica, Joseph Gonzalez, Liangsheng Yin, Pin-Lun Hsu, Shiyi Cao, Shu Liu, Tian Xia, Yang Zhou, Yichuan Wang, Yineng Zhang, Ying Sheng, Ziming Mao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T08:12:47Z","title":"Locality-aware Fair Scheduling in LLM Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14312","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:cf63157891cd5ce2cb4f9b5662d6dce16293979c8756f7b3080ff5fe3966d8a9","target":"record","created_at":"2026-07-05T10:04:48Z","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":"ca605e54e380ad31b29faca760cbc0914c6a0385f6c517bf9e5c9f7913975afc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T08:12:47Z","title_canon_sha256":"86f108b3c409acf7b20b98bfd5c788f59d4a43e3e5a6e13cd805c227a68e938e"},"schema_version":"1.0","source":{"id":"2501.14312","kind":"arxiv","version":1}},"canonical_sha256":"e3ad70b2d5707b2ec7ec152b24b69030712f196c821fed16bafdba429c01c2c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3ad70b2d5707b2ec7ec152b24b69030712f196c821fed16bafdba429c01c2c6","first_computed_at":"2026-07-05T10:04:48.650606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:48.650606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5tE3BOOZ5I9edWJlVtOimCJCFXStpamSq7X1TkfUXplOEA4QZxaL7UmiWPdtAH9CDEzr2r5pqUqKMDhsPp0FBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:48.651164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf63157891cd5ce2cb4f9b5662d6dce16293979c8756f7b3080ff5fe3966d8a9","sha256:85b0a4153788f46f20d9fcae53d27a71b19698c28196826c65cc1b317b371556"],"state_sha256":"a6df71b2251084c98172cd63d9c47c8589584e6baec8a2ce306a82b0e937ffc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cSgI9uCI86rrANi+AVQOzIS9RYs0w4SmRH6S7rSr/5u29kaWYMU9Wy0tSGRvBbe7D5TRIt+4DN3xh1ir2Z4HDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T13:59:34.665579Z","bundle_sha256":"86246469b56b99dfb4a2513580878a6c091479e916a2a8e54f22078e71fffe3b"}}