{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BP5OP5KMDYX3BPFN42TJLVV7KF","short_pith_number":"pith:BP5OP5KM","canonical_record":{"source":{"id":"2507.06608","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-07-09T07:27:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b80c5f03326e0b7c9fda5093a85a925b777fb4f38de62935a96833db011b3f5","abstract_canon_sha256":"a0a7658b7222745d17228df0e7eef9837c5d1fa8571bc8c49cdb79aa6c141ae7"},"schema_version":"1.0"},"canonical_sha256":"0bfae7f54c1e2fb0bcade6a695d6bf516df546dd9760ec4d1f9de07c9629ae03","source":{"kind":"arxiv","id":"2507.06608","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06608","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06608v5","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06608","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"pith_short_12","alias_value":"BP5OP5KMDYX3","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"pith_short_16","alias_value":"BP5OP5KMDYX3BPFN","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"pith_short_8","alias_value":"BP5OP5KM","created_at":"2026-07-05T11:49:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BP5OP5KMDYX3BPFN42TJLVV7KF","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06608","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-07-09T07:27:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b80c5f03326e0b7c9fda5093a85a925b777fb4f38de62935a96833db011b3f5","abstract_canon_sha256":"a0a7658b7222745d17228df0e7eef9837c5d1fa8571bc8c49cdb79aa6c141ae7"},"schema_version":"1.0"},"canonical_sha256":"0bfae7f54c1e2fb0bcade6a695d6bf516df546dd9760ec4d1f9de07c9629ae03","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:56.738059Z","signature_b64":"6DW2Gi3h8272vv536CGuAW1vvmRrrzMRhyOc8l/Nd/+6bPWmswwnCBMM4k/BDx0A/k7PmuS9BBuDPl1uyVfDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bfae7f54c1e2fb0bcade6a695d6bf516df546dd9760ec4d1f9de07c9629ae03","last_reissued_at":"2026-07-05T11:49:56.737545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:56.737545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06608","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nxowOpKMqf0uYIdsFovIk1GWq8oJltaGYAC75B9bLldwzWsoHDmuEdtRrg/SFwAcmfDACnrEH5HS5kWYKp4xBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:05:32.750252Z"},"content_sha256":"8347d64486567fcf08a301cb012b4ee37a1e9d25f47dad1cab34d9de95153e9c","schema_version":"1.0","event_id":"sha256:8347d64486567fcf08a301cb012b4ee37a1e9d25f47dad1cab34d9de95153e9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BP5OP5KMDYX3BPFN42TJLVV7KF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Colin Cai, Junjia Du, Xiaoxiang Shi, Zhihao Jia","submitted_at":"2025-07-09T07:27:18Z","abstract_excerpt":"Monolithic serving with chunked prefill improves GPU utilization by batching prefill and decode together, but suffers from fine-grained phase interference. Engine-level prefill-decode (PD) disaggregation avoids interference but incurs higher hardware and coordination overhead. Prior intra-GPU disaggregation approaches multiplex prefill and decode within a single GPU, using SLO-based tuning guided by heuristics from offline profiling or reactive feedback loops. However, these methods respond reactively to performance issues rather than anticipating them, limiting adaptability under dynamic work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06608","kind":"arxiv","version":5},"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/2507.06608/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":"2026-07-05T11:49:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GD4uaPU7woiSXX+3MgvaJ8nbvl+tcw6TNXsMZmbyq/Hnw1kK/IjumSw3/HuKL2cn337iAhgidml6ZyXLqYGeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:05:32.750596Z"},"content_sha256":"baefbe1425c8b366b005a9dc534d06843b08436cad2b1a058fe35b8de6f0e59e","schema_version":"1.0","event_id":"sha256:baefbe1425c8b366b005a9dc534d06843b08436cad2b1a058fe35b8de6f0e59e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BP5OP5KMDYX3BPFN42TJLVV7KF/bundle.json","state_url":"https://pith.science/pith/BP5OP5KMDYX3BPFN42TJLVV7KF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BP5OP5KMDYX3BPFN42TJLVV7KF/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":"2026-08-04T23:05:32Z","links":{"resolver":"https://pith.science/pith/BP5OP5KMDYX3BPFN42TJLVV7KF","bundle":"https://pith.science/pith/BP5OP5KMDYX3BPFN42TJLVV7KF/bundle.json","state":"https://pith.science/pith/BP5OP5KMDYX3BPFN42TJLVV7KF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BP5OP5KMDYX3BPFN42TJLVV7KF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BP5OP5KMDYX3BPFN42TJLVV7KF","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":"a0a7658b7222745d17228df0e7eef9837c5d1fa8571bc8c49cdb79aa6c141ae7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-07-09T07:27:18Z","title_canon_sha256":"1b80c5f03326e0b7c9fda5093a85a925b777fb4f38de62935a96833db011b3f5"},"schema_version":"1.0","source":{"id":"2507.06608","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06608","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06608v5","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06608","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"pith_short_12","alias_value":"BP5OP5KMDYX3","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"pith_short_16","alias_value":"BP5OP5KMDYX3BPFN","created_at":"2026-07-05T11:49:56Z"},{"alias_kind":"pith_short_8","alias_value":"BP5OP5KM","created_at":"2026-07-05T11:49:56Z"}],"graph_snapshots":[{"event_id":"sha256:baefbe1425c8b366b005a9dc534d06843b08436cad2b1a058fe35b8de6f0e59e","target":"graph","created_at":"2026-07-05T11:49:56Z","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/2507.06608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Monolithic serving with chunked prefill improves GPU utilization by batching prefill and decode together, but suffers from fine-grained phase interference. Engine-level prefill-decode (PD) disaggregation avoids interference but incurs higher hardware and coordination overhead. Prior intra-GPU disaggregation approaches multiplex prefill and decode within a single GPU, using SLO-based tuning guided by heuristics from offline profiling or reactive feedback loops. However, these methods respond reactively to performance issues rather than anticipating them, limiting adaptability under dynamic work","authors_text":"Colin Cai, Junjia Du, Xiaoxiang Shi, Zhihao Jia","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-07-09T07:27:18Z","title":"Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06608","kind":"arxiv","version":5},"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":"sha256:8347d64486567fcf08a301cb012b4ee37a1e9d25f47dad1cab34d9de95153e9c","target":"record","created_at":"2026-07-05T11:49:56Z","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":"a0a7658b7222745d17228df0e7eef9837c5d1fa8571bc8c49cdb79aa6c141ae7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-07-09T07:27:18Z","title_canon_sha256":"1b80c5f03326e0b7c9fda5093a85a925b777fb4f38de62935a96833db011b3f5"},"schema_version":"1.0","source":{"id":"2507.06608","kind":"arxiv","version":5}},"canonical_sha256":"0bfae7f54c1e2fb0bcade6a695d6bf516df546dd9760ec4d1f9de07c9629ae03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bfae7f54c1e2fb0bcade6a695d6bf516df546dd9760ec4d1f9de07c9629ae03","first_computed_at":"2026-07-05T11:49:56.737545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:56.737545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6DW2Gi3h8272vv536CGuAW1vvmRrrzMRhyOc8l/Nd/+6bPWmswwnCBMM4k/BDx0A/k7PmuS9BBuDPl1uyVfDAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:56.738059Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06608","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8347d64486567fcf08a301cb012b4ee37a1e9d25f47dad1cab34d9de95153e9c","sha256:baefbe1425c8b366b005a9dc534d06843b08436cad2b1a058fe35b8de6f0e59e"],"state_sha256":"687fbdbc450349aa8b58305c99d7ffcf5da8a65e6b3f5587efe1595085474200"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mtzN9nt8MpIzBgbGCA46Vtcw9dcQpIYIQVsaJMe5t8MiAe1EYYKtSyCN/5wFOLQxfuaOLto5g7DFyvjTtzoCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:05:32.753420Z","bundle_sha256":"bc943a67b9a8806b287c4f445d60c5db43034ab5733feb41613162dbff530e44"}}