{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C76TANP6Z6CRMYR3DSED5NTA3E","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":"ae10b4aa7e3acc25b4889e4053b85973006c941224ddbc1e7bfbba0edbd453b5","cross_cats_sorted":["cs.AI","cs.PF","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-03T05:01:51Z","title_canon_sha256":"ff8fe195eaf03fbbfa7c241f42fb5014057415356f1991c4fca590a448e3bc2f"},"schema_version":"1.0","source":{"id":"2306.02003","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02003","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02003v2","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02003","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"pith_short_12","alias_value":"C76TANP6Z6CR","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"pith_short_16","alias_value":"C76TANP6Z6CRMYR3","created_at":"2026-07-05T06:45:36Z"},{"alias_kind":"pith_short_8","alias_value":"C76TANP6","created_at":"2026-07-05T06:45:36Z"}],"graph_snapshots":[{"event_id":"sha256:1c780d67ec3185967f238a94a8f598b59270ec5a42a6236781d917d7d185b019","target":"graph","created_at":"2026-07-05T06:45:36Z","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/2306.02003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is hindered by the significant resource requirements during inference. In this paper, we study two approaches for mitigating these challenges: employing a cache to store previous queries and learning a model multiplexer to choose from an ensemble of models for query processing.\n  Theoretically, we provide an optimal algorithm for jointly optimizing both approach","authors_text":"Banghua Zhu, Clark Barrett, Jiantao Jiao, Lianmin Zheng, Michael I. Jordan, Ying Sheng","cross_cats":["cs.AI","cs.PF","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-03T05:01:51Z","title":"On Optimal Caching and Model Multiplexing for Large Model Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02003","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":"sha256:9f26598adf1e88e71702e3eb29141cc1c16a943f043e093d399b173639b0540a","target":"record","created_at":"2026-07-05T06:45:36Z","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":"ae10b4aa7e3acc25b4889e4053b85973006c941224ddbc1e7bfbba0edbd453b5","cross_cats_sorted":["cs.AI","cs.PF","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-03T05:01:51Z","title_canon_sha256":"ff8fe195eaf03fbbfa7c241f42fb5014057415356f1991c4fca590a448e3bc2f"},"schema_version":"1.0","source":{"id":"2306.02003","kind":"arxiv","version":2}},"canonical_sha256":"17fd3035fecf8516623b1c883eb660d93ccfa7117411cde87b084a8434f92192","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17fd3035fecf8516623b1c883eb660d93ccfa7117411cde87b084a8434f92192","first_computed_at":"2026-07-05T06:45:36.563725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:36.563725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gUGM1NJ/sKRf1mZFu/V7u9i8DpFYDtnF9SHSLxLXPvqLTxCnCBNht/CJUolVXLQ4ZuUDIS/scPPhyDM75WeNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:36.564225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02003","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f26598adf1e88e71702e3eb29141cc1c16a943f043e093d399b173639b0540a","sha256:1c780d67ec3185967f238a94a8f598b59270ec5a42a6236781d917d7d185b019"],"state_sha256":"a9eb018b6d24c96edd7bccf1e219d263ae8b8875fef30ed908148554ae0704c9"}