{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V5ELF5GEH6JTT2VKROP3MKWXL2","short_pith_number":"pith:V5ELF5GE","canonical_record":{"source":{"id":"2503.09304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T11:56:01Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"b4f95a974e764d13645a7839ea669d2a50b403bab1fc1d7cc7019785c91f65f6","abstract_canon_sha256":"4220e51b94752582a64953f9169f21ca469ebf84b345e331c0ee3b5191bdbc63"},"schema_version":"1.0"},"canonical_sha256":"af48b2f4c43f9339eaaa8b9fb62ad75eb82fbbd5627d34904e06b38b631bdb99","source":{"kind":"arxiv","id":"2503.09304","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09304","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09304v1","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09304","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_12","alias_value":"V5ELF5GEH6JT","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_16","alias_value":"V5ELF5GEH6JTT2VK","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_8","alias_value":"V5ELF5GE","created_at":"2026-07-05T10:29:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V5ELF5GEH6JTT2VKROP3MKWXL2","target":"record","payload":{"canonical_record":{"source":{"id":"2503.09304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T11:56:01Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"b4f95a974e764d13645a7839ea669d2a50b403bab1fc1d7cc7019785c91f65f6","abstract_canon_sha256":"4220e51b94752582a64953f9169f21ca469ebf84b345e331c0ee3b5191bdbc63"},"schema_version":"1.0"},"canonical_sha256":"af48b2f4c43f9339eaaa8b9fb62ad75eb82fbbd5627d34904e06b38b631bdb99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:53.657121Z","signature_b64":"pfKim/wOHO7aREow/BHbb2us9MOd9xlp5tS6xQK+LahH7weDjfd1YMOEsYTkRZdQ4VzyTjD8kNYMDFVDL1WCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af48b2f4c43f9339eaaa8b9fb62ad75eb82fbbd5627d34904e06b38b631bdb99","last_reissued_at":"2026-07-05T10:29:53.656349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:53.656349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.09304","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":"2026-07-05T10:29:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUWdi5K1tPQJ390LzI8ODnHnHyXeLawQnDBcIi1S4d8Od9/jFpWSQ6aUctSPU3ThC8V+w4qk15UaPytvF88QAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:47:24.749972Z"},"content_sha256":"2dd9914fcefa646826afddce889f7895c6dcf6aab304772b7fb79b935588e3e7","schema_version":"1.0","event_id":"sha256:2dd9914fcefa646826afddce889f7895c6dcf6aab304772b7fb79b935588e3e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V5ELF5GEH6JTT2VKROP3MKWXL2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Dejan Kostic, Faezeh Keshmiri Dindarloo, Marco Chiesa, Mohammad Siavashi","submitted_at":"2025-03-12T11:56:01Z","abstract_excerpt":"Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-sensitive (LS) and best-effort (BE) jobs. Existing inference systems employ iteration-level first-come-first-served scheduling, causing head-of-line blocking when BE jobs delay LS jobs. We introduce QLLM, a novel inference system designed for Mixture of Experts (MoE) models, featuring a fine-grained, priority-aware preemptive scheduler. QLLM enables expert-level preemption, deferring BE job execution while minimizing L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09304","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/2503.09304/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":"2026-07-05T10:29:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NG1GPZdnIcHA+J7O+fyCLoLX8opxnHpdkc9+CRy6TDEmcqA3bgUWeASXLpooeTISShidQgq3kkCpy3IWv+GSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:47:24.750461Z"},"content_sha256":"4124e4fd57129ed3368fe3074d8104050d74685a1c0fed42c57ae31bfd467b18","schema_version":"1.0","event_id":"sha256:4124e4fd57129ed3368fe3074d8104050d74685a1c0fed42c57ae31bfd467b18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V5ELF5GEH6JTT2VKROP3MKWXL2/bundle.json","state_url":"https://pith.science/pith/V5ELF5GEH6JTT2VKROP3MKWXL2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V5ELF5GEH6JTT2VKROP3MKWXL2/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":"2026-08-04T00:47:24Z","links":{"resolver":"https://pith.science/pith/V5ELF5GEH6JTT2VKROP3MKWXL2","bundle":"https://pith.science/pith/V5ELF5GEH6JTT2VKROP3MKWXL2/bundle.json","state":"https://pith.science/pith/V5ELF5GEH6JTT2VKROP3MKWXL2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V5ELF5GEH6JTT2VKROP3MKWXL2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V5ELF5GEH6JTT2VKROP3MKWXL2","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":"4220e51b94752582a64953f9169f21ca469ebf84b345e331c0ee3b5191bdbc63","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T11:56:01Z","title_canon_sha256":"b4f95a974e764d13645a7839ea669d2a50b403bab1fc1d7cc7019785c91f65f6"},"schema_version":"1.0","source":{"id":"2503.09304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09304","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09304v1","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09304","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_12","alias_value":"V5ELF5GEH6JT","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_16","alias_value":"V5ELF5GEH6JTT2VK","created_at":"2026-07-05T10:29:53Z"},{"alias_kind":"pith_short_8","alias_value":"V5ELF5GE","created_at":"2026-07-05T10:29:53Z"}],"graph_snapshots":[{"event_id":"sha256:4124e4fd57129ed3368fe3074d8104050d74685a1c0fed42c57ae31bfd467b18","target":"graph","created_at":"2026-07-05T10:29:53Z","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/2503.09304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-sensitive (LS) and best-effort (BE) jobs. Existing inference systems employ iteration-level first-come-first-served scheduling, causing head-of-line blocking when BE jobs delay LS jobs. We introduce QLLM, a novel inference system designed for Mixture of Experts (MoE) models, featuring a fine-grained, priority-aware preemptive scheduler. QLLM enables expert-level preemption, deferring BE job execution while minimizing L","authors_text":"Dejan Kostic, Faezeh Keshmiri Dindarloo, Marco Chiesa, Mohammad Siavashi","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T11:56:01Z","title":"Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09304","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":"sha256:2dd9914fcefa646826afddce889f7895c6dcf6aab304772b7fb79b935588e3e7","target":"record","created_at":"2026-07-05T10:29:53Z","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":"4220e51b94752582a64953f9169f21ca469ebf84b345e331c0ee3b5191bdbc63","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T11:56:01Z","title_canon_sha256":"b4f95a974e764d13645a7839ea669d2a50b403bab1fc1d7cc7019785c91f65f6"},"schema_version":"1.0","source":{"id":"2503.09304","kind":"arxiv","version":1}},"canonical_sha256":"af48b2f4c43f9339eaaa8b9fb62ad75eb82fbbd5627d34904e06b38b631bdb99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af48b2f4c43f9339eaaa8b9fb62ad75eb82fbbd5627d34904e06b38b631bdb99","first_computed_at":"2026-07-05T10:29:53.656349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:53.656349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pfKim/wOHO7aREow/BHbb2us9MOd9xlp5tS6xQK+LahH7weDjfd1YMOEsYTkRZdQ4VzyTjD8kNYMDFVDL1WCAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:53.657121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dd9914fcefa646826afddce889f7895c6dcf6aab304772b7fb79b935588e3e7","sha256:4124e4fd57129ed3368fe3074d8104050d74685a1c0fed42c57ae31bfd467b18"],"state_sha256":"6a1eded84b844b5bf4ada23f92b95e314a8be1b7e630ea78e3b7ddc08bb5a461"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2JcZoqmUEL15mVCnq1Vcgbb5SheM5Z6ZhFdoi4lgd5SobzVUyxHKUO4vvZ2oN4Xzjsm67EHz48RlWvQZgDG1DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:47:24.753962Z","bundle_sha256":"312e316660dd108b2fc8519ccd2adead2674e21b3298f85fc6147b151d06fb7d"}}