{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:27ZR6DSTKR6CK3IM7UNJCYBHJZ","short_pith_number":"pith:27ZR6DST","canonical_record":{"source":{"id":"2502.15763","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-14T16:00:00Z","cross_cats_sorted":["cs.AI","cs.AR","cs.LG"],"title_canon_sha256":"84b0e2a7354f80f6efab89140a302fcf8612ffdc788e0c2657d2a805b7447589","abstract_canon_sha256":"5b97fdd989b2a738853adb94327c81d00545651bec2947abec6588f6cd0d241e"},"schema_version":"1.0"},"canonical_sha256":"d7f31f0e53547c256d0cfd1a9160274e5d5ed4e6c88c7beca235916cdef3db44","source":{"kind":"arxiv","id":"2502.15763","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15763","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15763v1","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15763","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"pith_short_12","alias_value":"27ZR6DSTKR6C","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"pith_short_16","alias_value":"27ZR6DSTKR6CK3IM","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"pith_short_8","alias_value":"27ZR6DST","created_at":"2026-07-05T10:19:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:27ZR6DSTKR6CK3IM7UNJCYBHJZ","target":"record","payload":{"canonical_record":{"source":{"id":"2502.15763","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-14T16:00:00Z","cross_cats_sorted":["cs.AI","cs.AR","cs.LG"],"title_canon_sha256":"84b0e2a7354f80f6efab89140a302fcf8612ffdc788e0c2657d2a805b7447589","abstract_canon_sha256":"5b97fdd989b2a738853adb94327c81d00545651bec2947abec6588f6cd0d241e"},"schema_version":"1.0"},"canonical_sha256":"d7f31f0e53547c256d0cfd1a9160274e5d5ed4e6c88c7beca235916cdef3db44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:40.100762Z","signature_b64":"JYVrHGCsWIaWqmjNB/9KE5/UHHu8GQfez7s0wFQaflqCJEzjyN9TnSWN88zIOZTK9i8aIWnUqql1/2HYTyWrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7f31f0e53547c256d0cfd1a9160274e5d5ed4e6c88c7beca235916cdef3db44","last_reissued_at":"2026-07-05T10:19:40.100258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:40.100258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.15763","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":"2026-07-05T10:19:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tUEjE3ZRyoEbh1sr7PMhttUn5DyQFssbKLSI+DBMCeffb3AQtdKdPLlS47G5acKdY1fxG5RpOWzKhY170t2WAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:00:47.938198Z"},"content_sha256":"3ba298579052b077c50b9378c91a1c66d3338eb96e097cebd0b837f74cf9d893","schema_version":"1.0","event_id":"sha256:3ba298579052b077c50b9378c91a1c66d3338eb96e097cebd0b837f74cf9d893"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:27ZR6DSTKR6CK3IM7UNJCYBHJZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hybrid Offline-online Scheduling Method for Large Language Model Inference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.LG"],"primary_cat":"cs.DC","authors_text":"Bowen Pang, Feifan Wang, Kai Li, Ruifeng She","submitted_at":"2025-02-14T16:00:00Z","abstract_excerpt":"With the development of large language models (LLMs), it has become increasingly important to optimize hardware usage and improve throughput. In this paper, we study the inference optimization of the serving system that deploys LLMs. To optimize system throughput and maximize hardware utilization, we formulate the inference optimization problem as a mixed-integer programming (MIP) model and propose a hybrid offline-online method as solution. The offline method improves large-scale inference systems by introducing a Minimizing Makespan Bin Packing Problem. We further provide a theoretical lower"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15763","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/2502.15763/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":"2026-07-05T10:19:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LzM0j5atTnQz7cUUTlgJPO9rFfBQrnXkKXKj8wrOetQcRLIlr2P2lnEaWizy8C27YxgCD9j6HyaKVvjUE7UjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:00:47.938716Z"},"content_sha256":"426bbcee4f06781177957c904609edde10baa21333bec76548734139e2fcf023","schema_version":"1.0","event_id":"sha256:426bbcee4f06781177957c904609edde10baa21333bec76548734139e2fcf023"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/27ZR6DSTKR6CK3IM7UNJCYBHJZ/bundle.json","state_url":"https://pith.science/pith/27ZR6DSTKR6CK3IM7UNJCYBHJZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/27ZR6DSTKR6CK3IM7UNJCYBHJZ/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":"2026-08-06T06:00:47Z","links":{"resolver":"https://pith.science/pith/27ZR6DSTKR6CK3IM7UNJCYBHJZ","bundle":"https://pith.science/pith/27ZR6DSTKR6CK3IM7UNJCYBHJZ/bundle.json","state":"https://pith.science/pith/27ZR6DSTKR6CK3IM7UNJCYBHJZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/27ZR6DSTKR6CK3IM7UNJCYBHJZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:27ZR6DSTKR6CK3IM7UNJCYBHJZ","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":"5b97fdd989b2a738853adb94327c81d00545651bec2947abec6588f6cd0d241e","cross_cats_sorted":["cs.AI","cs.AR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-14T16:00:00Z","title_canon_sha256":"84b0e2a7354f80f6efab89140a302fcf8612ffdc788e0c2657d2a805b7447589"},"schema_version":"1.0","source":{"id":"2502.15763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15763","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15763v1","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15763","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"pith_short_12","alias_value":"27ZR6DSTKR6C","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"pith_short_16","alias_value":"27ZR6DSTKR6CK3IM","created_at":"2026-07-05T10:19:40Z"},{"alias_kind":"pith_short_8","alias_value":"27ZR6DST","created_at":"2026-07-05T10:19:40Z"}],"graph_snapshots":[{"event_id":"sha256:426bbcee4f06781177957c904609edde10baa21333bec76548734139e2fcf023","target":"graph","created_at":"2026-07-05T10:19:40Z","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/2502.15763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the development of large language models (LLMs), it has become increasingly important to optimize hardware usage and improve throughput. In this paper, we study the inference optimization of the serving system that deploys LLMs. To optimize system throughput and maximize hardware utilization, we formulate the inference optimization problem as a mixed-integer programming (MIP) model and propose a hybrid offline-online method as solution. The offline method improves large-scale inference systems by introducing a Minimizing Makespan Bin Packing Problem. We further provide a theoretical lower","authors_text":"Bowen Pang, Feifan Wang, Kai Li, Ruifeng She","cross_cats":["cs.AI","cs.AR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-14T16:00:00Z","title":"Hybrid Offline-online Scheduling Method for Large Language Model Inference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15763","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":"sha256:3ba298579052b077c50b9378c91a1c66d3338eb96e097cebd0b837f74cf9d893","target":"record","created_at":"2026-07-05T10:19:40Z","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":"5b97fdd989b2a738853adb94327c81d00545651bec2947abec6588f6cd0d241e","cross_cats_sorted":["cs.AI","cs.AR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-14T16:00:00Z","title_canon_sha256":"84b0e2a7354f80f6efab89140a302fcf8612ffdc788e0c2657d2a805b7447589"},"schema_version":"1.0","source":{"id":"2502.15763","kind":"arxiv","version":1}},"canonical_sha256":"d7f31f0e53547c256d0cfd1a9160274e5d5ed4e6c88c7beca235916cdef3db44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7f31f0e53547c256d0cfd1a9160274e5d5ed4e6c88c7beca235916cdef3db44","first_computed_at":"2026-07-05T10:19:40.100258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:40.100258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JYVrHGCsWIaWqmjNB/9KE5/UHHu8GQfez7s0wFQaflqCJEzjyN9TnSWN88zIOZTK9i8aIWnUqql1/2HYTyWrAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:40.100762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ba298579052b077c50b9378c91a1c66d3338eb96e097cebd0b837f74cf9d893","sha256:426bbcee4f06781177957c904609edde10baa21333bec76548734139e2fcf023"],"state_sha256":"f9f6887b163430ee8eca08cdb138c48aaf6c154cff062ceaf22d5e50d83b4279"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJrcsJvgOe9bgC/2RiZPCIxFiOn4LMfgOwOgCh2IKdK4y+Z13eANRj2g2ziitRYifIub7SEYiUaI3LodW/IKDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:00:47.942511Z","bundle_sha256":"db35b312503c28174514c76285ff4a6062557decb6716183ba0de80d01975e22"}}