{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VHHD5NGW66Q4EWTND5RFUML5H5","short_pith_number":"pith:VHHD5NGW","canonical_record":{"source":{"id":"2512.09472","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-12-10T09:47:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cebcc4b2a0041fc529b1603a048ba154dab91f02d181e5141f076f1e07808df0","abstract_canon_sha256":"639b55ad7cf2dd979fb1cdefc16ba87540d07234d0dfd4b7f5b19beaa49d9fb4"},"schema_version":"1.0"},"canonical_sha256":"a9ce3eb4d6f7a1c25a6d1f625a317d3f7f43a8e7cba97ecdd45c3fb1df40ca7b","source":{"kind":"arxiv","id":"2512.09472","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.09472","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2512.09472v2","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.09472","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"VHHD5NGW66Q4","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"VHHD5NGW66Q4EWTN","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"VHHD5NGW","created_at":"2026-05-22T01:03:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VHHD5NGW66Q4EWTND5RFUML5H5","target":"record","payload":{"canonical_record":{"source":{"id":"2512.09472","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-12-10T09:47:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cebcc4b2a0041fc529b1603a048ba154dab91f02d181e5141f076f1e07808df0","abstract_canon_sha256":"639b55ad7cf2dd979fb1cdefc16ba87540d07234d0dfd4b7f5b19beaa49d9fb4"},"schema_version":"1.0"},"canonical_sha256":"a9ce3eb4d6f7a1c25a6d1f625a317d3f7f43a8e7cba97ecdd45c3fb1df40ca7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:52.041985Z","signature_b64":"Nff9zWA17jDDX/QYSIUSk4WEyFlufxFZ5a6SjcitBgoGMm7Hg4tv82xeBIGN5z+v0LgmEeuY6oL82OOYs8VMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9ce3eb4d6f7a1c25a6d1f625a317d3f7f43a8e7cba97ecdd45c3fb1df40ca7b","last_reissued_at":"2026-05-22T01:03:52.041121Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:52.041121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.09472","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PUJ+25EDyDR0AZlQqQNWBYtibG+yiAzh+FqvZYZST1dmq0FTLIrra1nMC4YYlL9m/nIvoEQanEb7QvcS8GMgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T20:41:51.374483Z"},"content_sha256":"1bf20e18c428da0af3c47f9ee97844fc69204b4a6bdb0664f935feba8b762d09","schema_version":"1.0","event_id":"sha256:1bf20e18c428da0af3c47f9ee97844fc69204b4a6bdb0664f935feba8b762d09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VHHD5NGW66Q4EWTND5RFUML5H5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Chen Sun, Chiheng Lou, Pengcheng Wang, Rui Kang, Sheng Qi, Xin Jin, Xuanzhe Liu, Yong Zhang","submitted_at":"2025-12-10T09:47:40Z","abstract_excerpt":"Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems improve GPU utilization at the cost of degraded inference performance, particularly time-to-first-token (TTFT). We attribute this degradation to the lack of awareness regarding future workload characteristics. In contrast, recent analyses have shown the strong periodicity and long-term predictability of real-world LLM serving workloads. In this paper, we propose one-for-many GPU prewarming, which proactively loads parame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.09472","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/2512.09472/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":"2026-05-22T01:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"koJMttUszv+PeSAV2OW5vCrJCTzkunS0lu2edNcMU6n7OjdrCXFMaaLEDeRaAvY6a6fyQP18lr8HL/jjSA/+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T20:41:51.375220Z"},"content_sha256":"11d90e2b2146807ca6d5da32fff9253221f56ea4fa3f93e43e223653132ebc6d","schema_version":"1.0","event_id":"sha256:11d90e2b2146807ca6d5da32fff9253221f56ea4fa3f93e43e223653132ebc6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHHD5NGW66Q4EWTND5RFUML5H5/bundle.json","state_url":"https://pith.science/pith/VHHD5NGW66Q4EWTND5RFUML5H5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHHD5NGW66Q4EWTND5RFUML5H5/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":"2026-05-23T20:41:51Z","links":{"resolver":"https://pith.science/pith/VHHD5NGW66Q4EWTND5RFUML5H5","bundle":"https://pith.science/pith/VHHD5NGW66Q4EWTND5RFUML5H5/bundle.json","state":"https://pith.science/pith/VHHD5NGW66Q4EWTND5RFUML5H5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHHD5NGW66Q4EWTND5RFUML5H5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VHHD5NGW66Q4EWTND5RFUML5H5","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":"639b55ad7cf2dd979fb1cdefc16ba87540d07234d0dfd4b7f5b19beaa49d9fb4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-12-10T09:47:40Z","title_canon_sha256":"cebcc4b2a0041fc529b1603a048ba154dab91f02d181e5141f076f1e07808df0"},"schema_version":"1.0","source":{"id":"2512.09472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.09472","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2512.09472v2","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.09472","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"VHHD5NGW66Q4","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"VHHD5NGW66Q4EWTN","created_at":"2026-05-22T01:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"VHHD5NGW","created_at":"2026-05-22T01:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:11d90e2b2146807ca6d5da32fff9253221f56ea4fa3f93e43e223653132ebc6d","target":"graph","created_at":"2026-05-22T01:03:52Z","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/2512.09472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems improve GPU utilization at the cost of degraded inference performance, particularly time-to-first-token (TTFT). We attribute this degradation to the lack of awareness regarding future workload characteristics. In contrast, recent analyses have shown the strong periodicity and long-term predictability of real-world LLM serving workloads. In this paper, we propose one-for-many GPU prewarming, which proactively loads parame","authors_text":"Chen Sun, Chiheng Lou, Pengcheng Wang, Rui Kang, Sheng Qi, Xin Jin, Xuanzhe Liu, Yong Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-12-10T09:47:40Z","title":"WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.09472","kind":"arxiv","version":2},"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":"sha256:1bf20e18c428da0af3c47f9ee97844fc69204b4a6bdb0664f935feba8b762d09","target":"record","created_at":"2026-05-22T01:03:52Z","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":"639b55ad7cf2dd979fb1cdefc16ba87540d07234d0dfd4b7f5b19beaa49d9fb4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-12-10T09:47:40Z","title_canon_sha256":"cebcc4b2a0041fc529b1603a048ba154dab91f02d181e5141f076f1e07808df0"},"schema_version":"1.0","source":{"id":"2512.09472","kind":"arxiv","version":2}},"canonical_sha256":"a9ce3eb4d6f7a1c25a6d1f625a317d3f7f43a8e7cba97ecdd45c3fb1df40ca7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9ce3eb4d6f7a1c25a6d1f625a317d3f7f43a8e7cba97ecdd45c3fb1df40ca7b","first_computed_at":"2026-05-22T01:03:52.041121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:52.041121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nff9zWA17jDDX/QYSIUSk4WEyFlufxFZ5a6SjcitBgoGMm7Hg4tv82xeBIGN5z+v0LgmEeuY6oL82OOYs8VMCA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:52.041985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.09472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bf20e18c428da0af3c47f9ee97844fc69204b4a6bdb0664f935feba8b762d09","sha256:11d90e2b2146807ca6d5da32fff9253221f56ea4fa3f93e43e223653132ebc6d"],"state_sha256":"77d25bdca6ce4c6289d4461a7ae47574f5a7f62000cbb1e8b1346cd3c19c1f25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/4gwnQfyY7zsTBf9ScbAJxnOqO1CERz3v4JAMNN7C61KB/raoJJisXXc59zfn8B6zxgQr0Tg/0sEO7GTLiEsAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T20:41:51.379009Z","bundle_sha256":"969a46cdd0f8aa0b17e66d2a85369c791c28c5ad2e30a9206b046c6a8c3e178f"}}