{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GQ6TDGWHMDEAFRIALIVQO2VUE6","short_pith_number":"pith:GQ6TDGWH","schema_version":"1.0","canonical_sha256":"343d319ac760c802c5005a2b076ab42791702c77d68d1853609b2c1ba6c99ad3","source":{"kind":"arxiv","id":"2405.15130","version":1},"attestation_state":"computed","paper":{"title":"OptLLM: Optimal Assignment of Queries to Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Hongyu Zhang, Van-Hoang Le, Yuantian Miao, Yueyue Liu, Zhiqiang Li","submitted_at":"2024-05-24T01:05:37Z","abstract_excerpt":"Large Language Models (LLMs) have garnered considerable attention owing to their remarkable capabilities, leading to an increasing number of companies offering LLMs as services. Different LLMs achieve different performance at different costs. A challenge for users lies in choosing the LLMs that best fit their needs, balancing cost and performance. In this paper, we propose a framework for addressing the cost-effective query allocation problem for LLMs. Given a set of input queries and candidate LLMs, our framework, named OptLLM, provides users with a range of optimal solutions to choose from, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.15130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-05-24T01:05:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"96f58b8db17662bd200f883a6d4780be3deb0fbefa454e68a92842d56b464e41","abstract_canon_sha256":"cd12f8929d54b695bb0c1645ae6fb53529583d35e0862422984eded83c0caa97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:45.609660Z","signature_b64":"8/pxfa8G2QrA/MAY3gLY0CGLvDXBjvRLHOdbTyFaHwgV274JrjmRAbqyQk+DQz1zcfmMaCF0hYYAS6YAqMSBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"343d319ac760c802c5005a2b076ab42791702c77d68d1853609b2c1ba6c99ad3","last_reissued_at":"2026-07-05T08:22:45.609190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:45.609190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OptLLM: Optimal Assignment of Queries to Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Hongyu Zhang, Van-Hoang Le, Yuantian Miao, Yueyue Liu, Zhiqiang Li","submitted_at":"2024-05-24T01:05:37Z","abstract_excerpt":"Large Language Models (LLMs) have garnered considerable attention owing to their remarkable capabilities, leading to an increasing number of companies offering LLMs as services. Different LLMs achieve different performance at different costs. A challenge for users lies in choosing the LLMs that best fit their needs, balancing cost and performance. In this paper, we propose a framework for addressing the cost-effective query allocation problem for LLMs. Given a set of input queries and candidate LLMs, our framework, named OptLLM, provides users with a range of optimal solutions to choose from, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15130","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/2405.15130/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.15130","created_at":"2026-07-05T08:22:45.609248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15130v1","created_at":"2026-07-05T08:22:45.609248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15130","created_at":"2026-07-05T08:22:45.609248+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQ6TDGWHMDEA","created_at":"2026-07-05T08:22:45.609248+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQ6TDGWHMDEAFRIA","created_at":"2026-07-05T08:22:45.609248+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQ6TDGWH","created_at":"2026-07-05T08:22:45.609248+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07587","citing_title":"The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07303","citing_title":"KRONE: Scalable LLM-Augmented Log Anomaly Detection via Hierarchical Abstraction","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQ6TDGWHMDEAFRIALIVQO2VUE6","json":"https://pith.science/pith/GQ6TDGWHMDEAFRIALIVQO2VUE6.json","graph_json":"https://pith.science/api/pith-number/GQ6TDGWHMDEAFRIALIVQO2VUE6/graph.json","events_json":"https://pith.science/api/pith-number/GQ6TDGWHMDEAFRIALIVQO2VUE6/events.json","paper":"https://pith.science/paper/GQ6TDGWH"},"agent_actions":{"view_html":"https://pith.science/pith/GQ6TDGWHMDEAFRIALIVQO2VUE6","download_json":"https://pith.science/pith/GQ6TDGWHMDEAFRIALIVQO2VUE6.json","view_paper":"https://pith.science/paper/GQ6TDGWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15130&json=true","fetch_graph":"https://pith.science/api/pith-number/GQ6TDGWHMDEAFRIALIVQO2VUE6/graph.json","fetch_events":"https://pith.science/api/pith-number/GQ6TDGWHMDEAFRIALIVQO2VUE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQ6TDGWHMDEAFRIALIVQO2VUE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQ6TDGWHMDEAFRIALIVQO2VUE6/action/storage_attestation","attest_author":"https://pith.science/pith/GQ6TDGWHMDEAFRIALIVQO2VUE6/action/author_attestation","sign_citation":"https://pith.science/pith/GQ6TDGWHMDEAFRIALIVQO2VUE6/action/citation_signature","submit_replication":"https://pith.science/pith/GQ6TDGWHMDEAFRIALIVQO2VUE6/action/replication_record"}},"created_at":"2026-07-05T08:22:45.609248+00:00","updated_at":"2026-07-05T08:22:45.609248+00:00"}