{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HYIZBGKV64F3SCFYMO54VHTVZE","short_pith_number":"pith:HYIZBGKV","canonical_record":{"source":{"id":"2407.15309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-07-22T14:37:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d51e3152b85547b6eefcb29e32b3ec92eb84fa56f385776aac6becbc8870971","abstract_canon_sha256":"962b643a99f44f22ea515fc8e4faf310bc505bdcb748a3fbc2c0396df454cf56"},"schema_version":"1.0"},"canonical_sha256":"3e11909955f70bb908b863bbca9e75c9138c09ef1e62fe9e1435e11d90d0eb01","source":{"kind":"arxiv","id":"2407.15309","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15309","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15309v1","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15309","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"HYIZBGKV64F3","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"pith_short_16","alias_value":"HYIZBGKV64F3SCFY","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"pith_short_8","alias_value":"HYIZBGKV","created_at":"2026-07-05T08:46:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HYIZBGKV64F3SCFYMO54VHTVZE","target":"record","payload":{"canonical_record":{"source":{"id":"2407.15309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-07-22T14:37:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d51e3152b85547b6eefcb29e32b3ec92eb84fa56f385776aac6becbc8870971","abstract_canon_sha256":"962b643a99f44f22ea515fc8e4faf310bc505bdcb748a3fbc2c0396df454cf56"},"schema_version":"1.0"},"canonical_sha256":"3e11909955f70bb908b863bbca9e75c9138c09ef1e62fe9e1435e11d90d0eb01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:41.767649Z","signature_b64":"hR79i7qC11TmJQ2Bqqr8zPxqr1euM0NUw074qTV8q99Ej8URK8uu0DoDyT68AoblaD3arfLGkxkB/IWfFD8RDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e11909955f70bb908b863bbca9e75c9138c09ef1e62fe9e1435e11d90d0eb01","last_reissued_at":"2026-07-05T08:46:41.767152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:41.767152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.15309","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":"2026-07-05T08:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hwOKYU5ZleaKlPVXbssbw3RLRnL1VK+Ab5c6BVJUrcKvSWusnfN9GWhDBFCLNeuxiYu4Xw6UOIjfhZYkQNdmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:02:45.974643Z"},"content_sha256":"813e902e68551246abd2279623e9cee45a4a064edde2c7630ef57badb3ea6f94","schema_version":"1.0","event_id":"sha256:813e902e68551246abd2279623e9cee45a4a064edde2c7630ef57badb3ea6f94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HYIZBGKV64F3SCFYMO54VHTVZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Changxu Shao, Cong Guo, Feiyang Wu, Jiale Xu, Jingwen Leng, Junping Zhao, Ke Zhang, Minyi Guo, Rui Zhang, Shixuan Sun, Weiming Hu, Yu Feng, Yuhong Guo, Zihan Liu","submitted_at":"2024-07-22T14:37:58Z","abstract_excerpt":"Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value (KV) cache, a standard method for retaining previous computations, makes LLM inference highly bounded by memory. While batching strategies can enhance performance, they frequently lead to significant memory fragmentation. Even though cutting-edge systems like vLLM mitigate KV cache fragmentation using paged Attention mechanisms, they still suffer from ineff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15309","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/2407.15309/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":"2026-07-05T08:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uBeANoDf8NCMRvYU3VTaEIrvMaYbBEI+RSCAMJmi3seh42Vts9otE1ZPnxMejDmw8Yi2ikYAW4TCRHV41ZIwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:02:45.975593Z"},"content_sha256":"043b752376f059929e3700acbd26209a9ea9bb94d3f96bdd7c263e31db69f8b8","schema_version":"1.0","event_id":"sha256:043b752376f059929e3700acbd26209a9ea9bb94d3f96bdd7c263e31db69f8b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HYIZBGKV64F3SCFYMO54VHTVZE/bundle.json","state_url":"https://pith.science/pith/HYIZBGKV64F3SCFYMO54VHTVZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HYIZBGKV64F3SCFYMO54VHTVZE/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":"2026-08-09T03:02:45Z","links":{"resolver":"https://pith.science/pith/HYIZBGKV64F3SCFYMO54VHTVZE","bundle":"https://pith.science/pith/HYIZBGKV64F3SCFYMO54VHTVZE/bundle.json","state":"https://pith.science/pith/HYIZBGKV64F3SCFYMO54VHTVZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HYIZBGKV64F3SCFYMO54VHTVZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HYIZBGKV64F3SCFYMO54VHTVZE","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":"962b643a99f44f22ea515fc8e4faf310bc505bdcb748a3fbc2c0396df454cf56","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-07-22T14:37:58Z","title_canon_sha256":"4d51e3152b85547b6eefcb29e32b3ec92eb84fa56f385776aac6becbc8870971"},"schema_version":"1.0","source":{"id":"2407.15309","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15309","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15309v1","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15309","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"HYIZBGKV64F3","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"pith_short_16","alias_value":"HYIZBGKV64F3SCFY","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"pith_short_8","alias_value":"HYIZBGKV","created_at":"2026-07-05T08:46:41Z"}],"graph_snapshots":[{"event_id":"sha256:043b752376f059929e3700acbd26209a9ea9bb94d3f96bdd7c263e31db69f8b8","target":"graph","created_at":"2026-07-05T08:46:41Z","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/2407.15309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value (KV) cache, a standard method for retaining previous computations, makes LLM inference highly bounded by memory. While batching strategies can enhance performance, they frequently lead to significant memory fragmentation. Even though cutting-edge systems like vLLM mitigate KV cache fragmentation using paged Attention mechanisms, they still suffer from ineff","authors_text":"Changxu Shao, Cong Guo, Feiyang Wu, Jiale Xu, Jingwen Leng, Junping Zhao, Ke Zhang, Minyi Guo, Rui Zhang, Shixuan Sun, Weiming Hu, Yu Feng, Yuhong Guo, Zihan Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-07-22T14:37:58Z","title":"vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15309","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":"sha256:813e902e68551246abd2279623e9cee45a4a064edde2c7630ef57badb3ea6f94","target":"record","created_at":"2026-07-05T08:46:41Z","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":"962b643a99f44f22ea515fc8e4faf310bc505bdcb748a3fbc2c0396df454cf56","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-07-22T14:37:58Z","title_canon_sha256":"4d51e3152b85547b6eefcb29e32b3ec92eb84fa56f385776aac6becbc8870971"},"schema_version":"1.0","source":{"id":"2407.15309","kind":"arxiv","version":1}},"canonical_sha256":"3e11909955f70bb908b863bbca9e75c9138c09ef1e62fe9e1435e11d90d0eb01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e11909955f70bb908b863bbca9e75c9138c09ef1e62fe9e1435e11d90d0eb01","first_computed_at":"2026-07-05T08:46:41.767152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:41.767152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hR79i7qC11TmJQ2Bqqr8zPxqr1euM0NUw074qTV8q99Ej8URK8uu0DoDyT68AoblaD3arfLGkxkB/IWfFD8RDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:41.767649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15309","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:813e902e68551246abd2279623e9cee45a4a064edde2c7630ef57badb3ea6f94","sha256:043b752376f059929e3700acbd26209a9ea9bb94d3f96bdd7c263e31db69f8b8"],"state_sha256":"2898031c736f7e2c21c22b0b8cfb97ac2f33b418bee47aa0669a1bde19f53973"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1HPsUB44sAOprMGGdcVNgqORzNvusA37jaWJIlcfbYDfe58uD0USn1VzuutTLtMpk9PgDLNGlDc5EIp5+sZgCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:02:45.984555Z","bundle_sha256":"90a51a82ac1662e81f1d01124327285c13269f0446519c4c6ebf64136dfd23dc"}}