{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:A4NOSSWTED4Z77Q3MAO6BS45WF","short_pith_number":"pith:A4NOSSWT","canonical_record":{"source":{"id":"2508.20274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-27T21:15:41Z","cross_cats_sorted":[],"title_canon_sha256":"f20586fc94b94f9efc2778aa8b0113b78bab9ecc3799cfe848befaa8b1e16244","abstract_canon_sha256":"fac59c4df768227720a5ef8fb9c7cf91c118d4400e0805f91acf7338bfd1cad2"},"schema_version":"1.0"},"canonical_sha256":"071ae94ad320f99ffe1b601de0cb9db1630ff5ffee989759be71114548a260c7","source":{"kind":"arxiv","id":"2508.20274","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20274","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20274v1","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20274","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"pith_short_12","alias_value":"A4NOSSWTED4Z","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"pith_short_16","alias_value":"A4NOSSWTED4Z77Q3","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"pith_short_8","alias_value":"A4NOSSWT","created_at":"2026-07-05T12:00:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:A4NOSSWTED4Z77Q3MAO6BS45WF","target":"record","payload":{"canonical_record":{"source":{"id":"2508.20274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-27T21:15:41Z","cross_cats_sorted":[],"title_canon_sha256":"f20586fc94b94f9efc2778aa8b0113b78bab9ecc3799cfe848befaa8b1e16244","abstract_canon_sha256":"fac59c4df768227720a5ef8fb9c7cf91c118d4400e0805f91acf7338bfd1cad2"},"schema_version":"1.0"},"canonical_sha256":"071ae94ad320f99ffe1b601de0cb9db1630ff5ffee989759be71114548a260c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:33.416643Z","signature_b64":"igov9DsBHWT9pxNLrs4eFnps6QNo8/8y4oUsr7ZBXc6Ss0+6XXBC+M8HmnIw1BYjaIbR1HkVBaJETaA1PbssDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"071ae94ad320f99ffe1b601de0cb9db1630ff5ffee989759be71114548a260c7","last_reissued_at":"2026-07-05T12:00:33.416141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:33.416141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.20274","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":"2026-07-05T12:00:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+IaGrHNXshIhLD4IAqO0UIdNr8BQO3dC3zPxnQj6TBCKexf2PzjMx9WMcff8BR/xSyWgxt7WAIDz/iQTpVeFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:41:35.429474Z"},"content_sha256":"25173d7fe27430ff28ba64416d03ad1be40f1dc17b318b33c85e9006cddd9486","schema_version":"1.0","event_id":"sha256:25173d7fe27430ff28ba64416d03ad1be40f1dc17b318b33c85e9006cddd9486"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:A4NOSSWTED4Z77Q3MAO6BS45WF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predictable LLM Serving on GPU Clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Erfan Darzi, Shreeanant Bharadwaj, Sree Bhargavi Balija","submitted_at":"2025-08-27T21:15:41Z","abstract_excerpt":"Latency-sensitive inference on shared A100 clusters often suffers noisy-neighbor interference on the PCIe fabric, inflating tail latency and SLO violations. We present a fabric-agnostic, VM-deployable host-level controller that combines dynamic Multi-Instance GPU (MIG) reconfiguration, PCIe-aware placement, and lightweight guardrails (MPS quotas, cgroup I/O). It samples per-tenant tails and system signals, uses topology hints to avoid PCIe hot spots, and gates actions with dwell/cool-down to avoid thrash. On a single host and a 2-node (16-GPU) cluster, SLO miss-rate is reduced by \\(\\approx\\)32"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20274","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/2508.20274/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":"2026-07-05T12:00:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IpW6otP1qKG6mcXq5d7DZV5JMNRo4z+8nZ/PiIteGs7H5PLqtSmY/CqRa0GPpbZaFPB4oznsFBOZ3TXKCm2TCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:41:35.429844Z"},"content_sha256":"ab715afe589b9543083787a59d77118655498a5bccf212fcec0ea2c828e42161","schema_version":"1.0","event_id":"sha256:ab715afe589b9543083787a59d77118655498a5bccf212fcec0ea2c828e42161"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4NOSSWTED4Z77Q3MAO6BS45WF/bundle.json","state_url":"https://pith.science/pith/A4NOSSWTED4Z77Q3MAO6BS45WF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4NOSSWTED4Z77Q3MAO6BS45WF/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":"2026-07-06T15:41:35Z","links":{"resolver":"https://pith.science/pith/A4NOSSWTED4Z77Q3MAO6BS45WF","bundle":"https://pith.science/pith/A4NOSSWTED4Z77Q3MAO6BS45WF/bundle.json","state":"https://pith.science/pith/A4NOSSWTED4Z77Q3MAO6BS45WF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4NOSSWTED4Z77Q3MAO6BS45WF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A4NOSSWTED4Z77Q3MAO6BS45WF","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":"fac59c4df768227720a5ef8fb9c7cf91c118d4400e0805f91acf7338bfd1cad2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-27T21:15:41Z","title_canon_sha256":"f20586fc94b94f9efc2778aa8b0113b78bab9ecc3799cfe848befaa8b1e16244"},"schema_version":"1.0","source":{"id":"2508.20274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20274","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20274v1","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20274","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"pith_short_12","alias_value":"A4NOSSWTED4Z","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"pith_short_16","alias_value":"A4NOSSWTED4Z77Q3","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"pith_short_8","alias_value":"A4NOSSWT","created_at":"2026-07-05T12:00:33Z"}],"graph_snapshots":[{"event_id":"sha256:ab715afe589b9543083787a59d77118655498a5bccf212fcec0ea2c828e42161","target":"graph","created_at":"2026-07-05T12:00:33Z","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/2508.20274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Latency-sensitive inference on shared A100 clusters often suffers noisy-neighbor interference on the PCIe fabric, inflating tail latency and SLO violations. We present a fabric-agnostic, VM-deployable host-level controller that combines dynamic Multi-Instance GPU (MIG) reconfiguration, PCIe-aware placement, and lightweight guardrails (MPS quotas, cgroup I/O). It samples per-tenant tails and system signals, uses topology hints to avoid PCIe hot spots, and gates actions with dwell/cool-down to avoid thrash. On a single host and a 2-node (16-GPU) cluster, SLO miss-rate is reduced by \\(\\approx\\)32","authors_text":"Erfan Darzi, Shreeanant Bharadwaj, Sree Bhargavi Balija","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-27T21:15:41Z","title":"Predictable LLM Serving on GPU Clusters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20274","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":"sha256:25173d7fe27430ff28ba64416d03ad1be40f1dc17b318b33c85e9006cddd9486","target":"record","created_at":"2026-07-05T12:00:33Z","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":"fac59c4df768227720a5ef8fb9c7cf91c118d4400e0805f91acf7338bfd1cad2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-27T21:15:41Z","title_canon_sha256":"f20586fc94b94f9efc2778aa8b0113b78bab9ecc3799cfe848befaa8b1e16244"},"schema_version":"1.0","source":{"id":"2508.20274","kind":"arxiv","version":1}},"canonical_sha256":"071ae94ad320f99ffe1b601de0cb9db1630ff5ffee989759be71114548a260c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"071ae94ad320f99ffe1b601de0cb9db1630ff5ffee989759be71114548a260c7","first_computed_at":"2026-07-05T12:00:33.416141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:33.416141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"igov9DsBHWT9pxNLrs4eFnps6QNo8/8y4oUsr7ZBXc6Ss0+6XXBC+M8HmnIw1BYjaIbR1HkVBaJETaA1PbssDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:33.416643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25173d7fe27430ff28ba64416d03ad1be40f1dc17b318b33c85e9006cddd9486","sha256:ab715afe589b9543083787a59d77118655498a5bccf212fcec0ea2c828e42161"],"state_sha256":"446d94c838d13ccecdbe568094b6641c45260c78ba0983bbe7646002046bdeb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VLrINVd52WD5MwEwcB+6KKE72fR47GdnK+UVleBEXsipkzyhbr9IlocRZG2COlIOPoP93bE60dIGU5Cmu9RBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:41:35.431926Z","bundle_sha256":"30f5fc9abc8c55ac45c068e8260dfd06bdf352e4edc61d9d66d42ca1c3049243"}}