{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C5QHJLTU3GSDZD22G5ATVQCQLQ","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":"c28c647b8f3ac9856e14bc2b0ee94df0e1bd1de9247614002859008c7e78c02f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-08-14T21:46:37Z","title_canon_sha256":"b7a3442095d38bf34e7181104bda385b0de5391c48d53d7989c0c759d050a4f6"},"schema_version":"1.0","source":{"id":"2308.07470","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.07470","created_at":"2026-07-05T07:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2308.07470v2","created_at":"2026-07-05T07:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07470","created_at":"2026-07-05T07:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"C5QHJLTU3GSD","created_at":"2026-07-05T07:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"C5QHJLTU3GSDZD22","created_at":"2026-07-05T07:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"C5QHJLTU","created_at":"2026-07-05T07:50:20Z"}],"graph_snapshots":[{"event_id":"sha256:b9bc47ca7f06104cbfbb7153e297e8a33cd69bb8f68a212fd15ce3e026600b98","target":"graph","created_at":"2026-07-05T07:50:20Z","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/2308.07470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Having large batch sizes is one of the most critical aspects of increasing the accelerator efficiency and the performance of DNN model inference. However, existing model serving systems cannot achieve adequate batch sizes while meeting latency objectives as these systems eagerly dispatch requests to accelerators to minimize the accelerator idle time. We propose Symphony, a DNN serving system that explores deferred batch scheduling to optimize system efficiency and throughput. Further, unlike other prior systems, Symphony's GPU usage is load-proportional: it consolidates workloads on the approp","authors_text":"Anirudh Canumalla, Arvind Krishnamurthy, Danyang Zhuo, Lequn Chen, Matthai Philipose, Weixin Deng, Yu Xin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-08-14T21:46:37Z","title":"Symphony: Optimized DNN Model Serving using Deferred Batch Scheduling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07470","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:cc221bed26fd09f897ec417ad634a6046aef2c5c713c4317d64385c912111df7","target":"record","created_at":"2026-07-05T07:50:20Z","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":"c28c647b8f3ac9856e14bc2b0ee94df0e1bd1de9247614002859008c7e78c02f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-08-14T21:46:37Z","title_canon_sha256":"b7a3442095d38bf34e7181104bda385b0de5391c48d53d7989c0c759d050a4f6"},"schema_version":"1.0","source":{"id":"2308.07470","kind":"arxiv","version":2}},"canonical_sha256":"176074ae74d9a43c8f5a37413ac0505c0f1344e09d84a4c306a865a408600985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"176074ae74d9a43c8f5a37413ac0505c0f1344e09d84a4c306a865a408600985","first_computed_at":"2026-07-05T07:50:20.098256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:20.098256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ghUNGN2NBTtI9U/Z21SFohBxXTWgtqDDpJCl7mSXja00RshYkUzEr2uLhAh0QvbOa5c7LhMY0o8M8ElYnbjkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:20.098686Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.07470","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc221bed26fd09f897ec417ad634a6046aef2c5c713c4317d64385c912111df7","sha256:b9bc47ca7f06104cbfbb7153e297e8a33cd69bb8f68a212fd15ce3e026600b98"],"state_sha256":"d4cc6dca8a65e08fce6576e4590dba5d22f098951ffd36b9ec247c3077499f67"}