{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2AZTGHUDIG7IHGYSE66PG4XTXT","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":"5fe1246e844fded5fbf4b7e12b110067ae826347f1467219f678d64d5449794f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-11-30T01:36:46Z","title_canon_sha256":"f7ae5c982962f239a54469105d18a8a97d9b206ca4ecbd2498f62b7add97a553"},"schema_version":"1.0","source":{"id":"2311.18174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18174","created_at":"2026-07-05T07:18:38Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18174v1","created_at":"2026-07-05T07:18:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18174","created_at":"2026-07-05T07:18:38Z"},{"alias_kind":"pith_short_12","alias_value":"2AZTGHUDIG7I","created_at":"2026-07-05T07:18:38Z"},{"alias_kind":"pith_short_16","alias_value":"2AZTGHUDIG7IHGYS","created_at":"2026-07-05T07:18:38Z"},{"alias_kind":"pith_short_8","alias_value":"2AZTGHUD","created_at":"2026-07-05T07:18:38Z"}],"graph_snapshots":[{"event_id":"sha256:d9043c0a592fab1ae3c2635c79f8b98c73d645969e772545a242fa439073cb9e","target":"graph","created_at":"2026-07-05T07:18:38Z","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/2311.18174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we investigate how to push the performance limits of serving Deep Neural Network (DNN) models on CPU-based servers. Specifically, we observe that while intra-operator parallelism across multiple threads is an effective way to reduce inference latency, it provides diminishing returns. Our primary insight is that instead of running a single instance of a model with all available threads on a server, running multiple instances each with smaller batch sizes and fewer threads for intra-op parallelism can provide lower inference latency. However, the right configuration is hard to det","authors_text":"Amar Phanishayee, Ankit Bhardwaj, Deepak Narayanan, Mihail Tarta, Ryan Stutsman","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-11-30T01:36:46Z","title":"Packrat: Automatic Reconfiguration for Latency Minimization in CPU-based DNN Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18174","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":"sha256:15534c12b6203723ce4b0e585c3cc2455af37beb5f299ae596d00d0b75956af0","target":"record","created_at":"2026-07-05T07:18:38Z","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":"5fe1246e844fded5fbf4b7e12b110067ae826347f1467219f678d64d5449794f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-11-30T01:36:46Z","title_canon_sha256":"f7ae5c982962f239a54469105d18a8a97d9b206ca4ecbd2498f62b7add97a553"},"schema_version":"1.0","source":{"id":"2311.18174","kind":"arxiv","version":1}},"canonical_sha256":"d033331e8341be839b1227bcf372f3bcd11aeda3a27281716cb57c6a6115f2ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d033331e8341be839b1227bcf372f3bcd11aeda3a27281716cb57c6a6115f2ae","first_computed_at":"2026-07-05T07:18:38.081470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:38.081470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Z27RJ9Igdu5y7vFAkwHue1e947PFooLRfP7R9YJlTrgKoFkNkd88W4PlBpVQf4s6CVAU58FyqSLt8kipOPUDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:38.081856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.18174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15534c12b6203723ce4b0e585c3cc2455af37beb5f299ae596d00d0b75956af0","sha256:d9043c0a592fab1ae3c2635c79f8b98c73d645969e772545a242fa439073cb9e"],"state_sha256":"7438b9be2f8663489be735c254f9d6e60557f0f251a4dfecd88bd0a57cc0c96f"}