{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GIOKATMP3M6GL7CSRUDVBU6GNC","short_pith_number":"pith:GIOKATMP","canonical_record":{"source":{"id":"2602.02987","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-02-03T01:47:37Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"5365ecd1bdc179db4d45051d1a4f22a92728778a969b4c9064b38bce1dbdae38","abstract_canon_sha256":"8c4bd1952e705e13c95e6a83d3a2593979622fa6a252883d8808c216cc66ea76"},"schema_version":"1.0"},"canonical_sha256":"321ca04d8fdb3c65fc528d0750d3c668a8671e04f813d3f79cfaac8856104d0f","source":{"kind":"arxiv","id":"2602.02987","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.02987","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.02987v2","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02987","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"pith_short_12","alias_value":"GIOKATMP3M6G","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"pith_short_16","alias_value":"GIOKATMP3M6GL7CS","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"pith_short_8","alias_value":"GIOKATMP","created_at":"2026-06-05T01:14:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GIOKATMP3M6GL7CSRUDVBU6GNC","target":"record","payload":{"canonical_record":{"source":{"id":"2602.02987","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-02-03T01:47:37Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"5365ecd1bdc179db4d45051d1a4f22a92728778a969b4c9064b38bce1dbdae38","abstract_canon_sha256":"8c4bd1952e705e13c95e6a83d3a2593979622fa6a252883d8808c216cc66ea76"},"schema_version":"1.0"},"canonical_sha256":"321ca04d8fdb3c65fc528d0750d3c668a8671e04f813d3f79cfaac8856104d0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:34.250659Z","signature_b64":"GA1XfuCP1VDHgaBE9aCvr9fXXUPxXps1KBj45mye4VIg7yW9GnnNAOEl1hLeoFj9Y862dgnM8VHq7/v66Dw6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"321ca04d8fdb3c65fc528d0750d3c668a8671e04f813d3f79cfaac8856104d0f","last_reissued_at":"2026-06-05T01:14:34.249796Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:34.249796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.02987","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":"2026-06-05T01:14:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UTd0qeXpVEXBRmfo1uvWllKoyxvOC3qz/ovQwwIy55H5mAiTq+NdB/96lDLlpV7VmpRIKhF0F4pvrRAsQnEzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:18:42.006339Z"},"content_sha256":"7a89a6c72cd9afef442a45fd77826133cba6a3f4be2cc583603553e12ebfca30","schema_version":"1.0","event_id":"sha256:7a89a6c72cd9afef442a45fd77826133cba6a3f4be2cc583603553e12ebfca30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GIOKATMP3M6GL7CSRUDVBU6GNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.DC","authors_text":"Jiheng Zhang, Ruihan Lin, Zean Han, Zezhen Ding","submitted_at":"2026-02-03T01:47:37Z","abstract_excerpt":"Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM inference: a compute-intensive \\emph{prefill} phase that processes user input, followed by a memory-bound \\emph{decode} phase that generates output tokens. When these phases share GPU resources, prefill tasks throttle the processing speed of concurrent decodes, creating state-dependent contention. This contention is further complicated by workload heterogeneity, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02987","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/2602.02987/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":"2026-06-05T01:14:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/8ZjTAk6cSkSSU4cJ4JA9o22kKt55YA0z/3xyvvIhLMyU8uHAtYLAsWcyYcpLHBhIWFP0hSdR3zDNh8FlOoEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:18:42.006821Z"},"content_sha256":"f0f435b00d5d2c0ddc1dedd6803dce9364a2744f9aa2b764edae6005e93330c2","schema_version":"1.0","event_id":"sha256:f0f435b00d5d2c0ddc1dedd6803dce9364a2744f9aa2b764edae6005e93330c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GIOKATMP3M6GL7CSRUDVBU6GNC/bundle.json","state_url":"https://pith.science/pith/GIOKATMP3M6GL7CSRUDVBU6GNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GIOKATMP3M6GL7CSRUDVBU6GNC/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":"2026-06-06T08:18:42Z","links":{"resolver":"https://pith.science/pith/GIOKATMP3M6GL7CSRUDVBU6GNC","bundle":"https://pith.science/pith/GIOKATMP3M6GL7CSRUDVBU6GNC/bundle.json","state":"https://pith.science/pith/GIOKATMP3M6GL7CSRUDVBU6GNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GIOKATMP3M6GL7CSRUDVBU6GNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GIOKATMP3M6GL7CSRUDVBU6GNC","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":"8c4bd1952e705e13c95e6a83d3a2593979622fa6a252883d8808c216cc66ea76","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-02-03T01:47:37Z","title_canon_sha256":"5365ecd1bdc179db4d45051d1a4f22a92728778a969b4c9064b38bce1dbdae38"},"schema_version":"1.0","source":{"id":"2602.02987","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.02987","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.02987v2","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02987","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"pith_short_12","alias_value":"GIOKATMP3M6G","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"pith_short_16","alias_value":"GIOKATMP3M6GL7CS","created_at":"2026-06-05T01:14:34Z"},{"alias_kind":"pith_short_8","alias_value":"GIOKATMP","created_at":"2026-06-05T01:14:34Z"}],"graph_snapshots":[{"event_id":"sha256:f0f435b00d5d2c0ddc1dedd6803dce9364a2744f9aa2b764edae6005e93330c2","target":"graph","created_at":"2026-06-05T01:14:34Z","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/2602.02987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM inference: a compute-intensive \\emph{prefill} phase that processes user input, followed by a memory-bound \\emph{decode} phase that generates output tokens. When these phases share GPU resources, prefill tasks throttle the processing speed of concurrent decodes, creating state-dependent contention. This contention is further complicated by workload heterogeneity, a","authors_text":"Jiheng Zhang, Ruihan Lin, Zean Han, Zezhen Ding","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-02-03T01:47:37Z","title":"Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02987","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":"sha256:7a89a6c72cd9afef442a45fd77826133cba6a3f4be2cc583603553e12ebfca30","target":"record","created_at":"2026-06-05T01:14:34Z","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":"8c4bd1952e705e13c95e6a83d3a2593979622fa6a252883d8808c216cc66ea76","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-02-03T01:47:37Z","title_canon_sha256":"5365ecd1bdc179db4d45051d1a4f22a92728778a969b4c9064b38bce1dbdae38"},"schema_version":"1.0","source":{"id":"2602.02987","kind":"arxiv","version":2}},"canonical_sha256":"321ca04d8fdb3c65fc528d0750d3c668a8671e04f813d3f79cfaac8856104d0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"321ca04d8fdb3c65fc528d0750d3c668a8671e04f813d3f79cfaac8856104d0f","first_computed_at":"2026-06-05T01:14:34.249796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:34.249796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GA1XfuCP1VDHgaBE9aCvr9fXXUPxXps1KBj45mye4VIg7yW9GnnNAOEl1hLeoFj9Y862dgnM8VHq7/v66Dw6AQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:34.250659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.02987","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a89a6c72cd9afef442a45fd77826133cba6a3f4be2cc583603553e12ebfca30","sha256:f0f435b00d5d2c0ddc1dedd6803dce9364a2744f9aa2b764edae6005e93330c2"],"state_sha256":"fa578d33446694c42b42e4a8434c7e5d6629cd3b6693ad1d3bec385edba9f30f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wce1DrEbxeNjDaAtagQrbLFFZxzWje3W3UPXX02sebJlLADLHoSSHO9c7sBeZdVUeLnIYT4HnFpJFzBU07F0CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T08:18:42.010993Z","bundle_sha256":"b2949fb4214cf31f2b975338ede3bb192506bbf9d501e0481299a44d43f73fc5"}}