{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KITIJ35TOQZLX6IIDQP46OFKIL","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":"da483c0a6d11bcbb1fe4f4b692d5dd47e60e3382cf6cdfc80ebd3bb43b28d099","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-06-17T03:49:25Z","title_canon_sha256":"19837c73065ea53ad3a558f43811176d307fb203c467fef6e2e23e660d685846"},"schema_version":"1.0","source":{"id":"2506.14851","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14851","created_at":"2026-06-30T02:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14851v1","created_at":"2026-06-30T02:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14851","created_at":"2026-06-30T02:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"KITIJ35TOQZL","created_at":"2026-06-30T02:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"KITIJ35TOQZLX6II","created_at":"2026-06-30T02:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"KITIJ35T","created_at":"2026-06-30T02:16:52Z"}],"graph_snapshots":[{"event_id":"sha256:28902b04428eb31b3cd3f51a4ae18d141e3aa2d7672949868e6e6ed5bb25066b","target":"graph","created_at":"2026-06-30T02:16:52Z","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/2506.14851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Applications based on Large Language Models (LLMs) contains a series of tasks to address real-world problems with boosted capability, which have dynamic demand volumes on diverse backends. Existing serving systems treat the resource demands of LLM applications as a blackbox, compromising end-to-end efficiency due to improper queuing order and backend warm up latency. We find that the resource demands of LLM applications can be modeled in a general and accurate manner with Probabilistic Demand Graph (PDGraph). We then propose Hermes, which leverages PDGraph for efficient serving of LLM applicat","authors_text":"Chen Chen, Minyi Guo, Shixuan Sun, Weiye Wang, Xusheng Chen, Yifei Liu, Yifei Zhu, Yizhou Shan, Zhenghao Gan, Zhenhua Han, Zuo Gan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-06-17T03:49:25Z","title":"Efficient Serving of LLM Applications with Probabilistic Demand Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14851","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":"sha256:9542e751837e579486b4e4da1863ed16cce8aec5e0cd3783b1eed6eb462c4478","target":"record","created_at":"2026-06-30T02:16:52Z","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":"da483c0a6d11bcbb1fe4f4b692d5dd47e60e3382cf6cdfc80ebd3bb43b28d099","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-06-17T03:49:25Z","title_canon_sha256":"19837c73065ea53ad3a558f43811176d307fb203c467fef6e2e23e660d685846"},"schema_version":"1.0","source":{"id":"2506.14851","kind":"arxiv","version":1}},"canonical_sha256":"522684efb37432bbf9081c1fcf38aa42f9fe0d16d7c3fc7e5925da7f38ef5c54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"522684efb37432bbf9081c1fcf38aa42f9fe0d16d7c3fc7e5925da7f38ef5c54","first_computed_at":"2026-06-30T02:16:52.605368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:16:52.605368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UJaDe4eDX+aAdGrEcCOjrxv9H6LFpUJsWnZEk76jMHrHaG6c+gfZX0zAXsuJ06csVJRAkGZlRJI9TBSkExN0Dw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:16:52.605988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14851","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9542e751837e579486b4e4da1863ed16cce8aec5e0cd3783b1eed6eb462c4478","sha256:28902b04428eb31b3cd3f51a4ae18d141e3aa2d7672949868e6e6ed5bb25066b"],"state_sha256":"abad9e53804ac6c50e8e61b143349bb61e75aa4ca99eb8da91e42569bfc9efb7"}