{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4F7AQJCL7OSUSTNHZDIVXRTMCX","short_pith_number":"pith:4F7AQJCL","schema_version":"1.0","canonical_sha256":"e17e08244bfba5494da7c8d15bc66c15c0289358558cf537b9a00a8d04dfa98b","source":{"kind":"arxiv","id":"2405.16587","version":2},"attestation_state":"computed","paper":{"title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"Anqi Yu, Jin Li, John C.S. Lui, Xiangxiang Dai, Xutong Liu","submitted_at":"2024-05-26T14:38:24Z","abstract_excerpt":"With the rapid advancement of large language models (LLMs), the diversity of multi-LLM tasks and the variability in their pricing structures have become increasingly important, as costs can vary greatly between different LLMs. To tackle these challenges, we introduce the \\textit{C2MAB-V}, a \\underline{C}ost-effective \\underline{C}ombinatorial \\underline{M}ulti-armed \\underline{B}andit with \\underline{V}ersatile reward models for optimal LLM selection and usage. This online model differs from traditional static approaches or those reliant on a single LLM without cost consideration. With multipl"},"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":"2405.16587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T14:38:24Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"0e3bc527cd102d3e1223d8d8c9730e33e41923a5be07181c94e54b592d383f03","abstract_canon_sha256":"06a6e52f2e052e7fc86e69675a3f164094f475802612fdba3f4d0fc2cecf3843"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:33.389630Z","signature_b64":"6PYqweomEPMvS8eg+rLRB7Ldm8m1LzpXjeedaVw7ZIXOXJgwr5A1ktgmKHtCvnz3ACMWS+xmW3RnACw3WxRTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e17e08244bfba5494da7c8d15bc66c15c0289358558cf537b9a00a8d04dfa98b","last_reissued_at":"2026-07-05T09:14:33.389087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:33.389087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"Anqi Yu, Jin Li, John C.S. Lui, Xiangxiang Dai, Xutong Liu","submitted_at":"2024-05-26T14:38:24Z","abstract_excerpt":"With the rapid advancement of large language models (LLMs), the diversity of multi-LLM tasks and the variability in their pricing structures have become increasingly important, as costs can vary greatly between different LLMs. To tackle these challenges, we introduce the \\textit{C2MAB-V}, a \\underline{C}ost-effective \\underline{C}ombinatorial \\underline{M}ulti-armed \\underline{B}andit with \\underline{V}ersatile reward models for optimal LLM selection and usage. This online model differs from traditional static approaches or those reliant on a single LLM without cost consideration. With multipl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16587","kind":"arxiv","version":2},"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/2405.16587/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":"2405.16587","created_at":"2026-07-05T09:14:33.389147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16587v2","created_at":"2026-07-05T09:14:33.389147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16587","created_at":"2026-07-05T09:14:33.389147+00:00"},{"alias_kind":"pith_short_12","alias_value":"4F7AQJCL7OSU","created_at":"2026-07-05T09:14:33.389147+00:00"},{"alias_kind":"pith_short_16","alias_value":"4F7AQJCL7OSUSTNH","created_at":"2026-07-05T09:14:33.389147+00:00"},{"alias_kind":"pith_short_8","alias_value":"4F7AQJCL","created_at":"2026-07-05T09:14:33.389147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17489","citing_title":"Online LLM Selection via Constrained Bandits with Time-Varying Demand","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07303","citing_title":"KRONE: Scalable LLM-Augmented Log Anomaly Detection via Hierarchical Abstraction","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20021","citing_title":"Continuous Semantic Caching for Low-Cost LLM Serving","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4F7AQJCL7OSUSTNHZDIVXRTMCX","json":"https://pith.science/pith/4F7AQJCL7OSUSTNHZDIVXRTMCX.json","graph_json":"https://pith.science/api/pith-number/4F7AQJCL7OSUSTNHZDIVXRTMCX/graph.json","events_json":"https://pith.science/api/pith-number/4F7AQJCL7OSUSTNHZDIVXRTMCX/events.json","paper":"https://pith.science/paper/4F7AQJCL"},"agent_actions":{"view_html":"https://pith.science/pith/4F7AQJCL7OSUSTNHZDIVXRTMCX","download_json":"https://pith.science/pith/4F7AQJCL7OSUSTNHZDIVXRTMCX.json","view_paper":"https://pith.science/paper/4F7AQJCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16587&json=true","fetch_graph":"https://pith.science/api/pith-number/4F7AQJCL7OSUSTNHZDIVXRTMCX/graph.json","fetch_events":"https://pith.science/api/pith-number/4F7AQJCL7OSUSTNHZDIVXRTMCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4F7AQJCL7OSUSTNHZDIVXRTMCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4F7AQJCL7OSUSTNHZDIVXRTMCX/action/storage_attestation","attest_author":"https://pith.science/pith/4F7AQJCL7OSUSTNHZDIVXRTMCX/action/author_attestation","sign_citation":"https://pith.science/pith/4F7AQJCL7OSUSTNHZDIVXRTMCX/action/citation_signature","submit_replication":"https://pith.science/pith/4F7AQJCL7OSUSTNHZDIVXRTMCX/action/replication_record"}},"created_at":"2026-07-05T09:14:33.389147+00:00","updated_at":"2026-07-05T09:14:33.389147+00:00"}