{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XVHB66OTKJMQNJM6JYND2WYH5A","short_pith_number":"pith:XVHB66OT","schema_version":"1.0","canonical_sha256":"bd4e1f79d3525906a59e4e1a3d5b07e83b9bf1146ad60cc14169fab0f637b4eb","source":{"kind":"arxiv","id":"2502.00409","version":3},"attestation_state":"computed","paper":{"title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Antoine Gourru, Christophe Bouvard, Clovis Varangot-Reille, Fran\\c{c}ois Jacquenet, Marion Schaeffer, Mathieu Ciancone","submitted_at":"2025-02-01T12:08:38Z","abstract_excerpt":"Large Language Model (LLM)-based systems, i.e. interconnected elements that include an LLM as a central component, such as conversational agents, are usually designed with monolithic, static architectures that rely on a single, general-purpose LLM to handle all user queries. However, these systems may be inefficient as different queries may require different levels of reasoning, domain knowledge or pre-processing. While generalist LLMs (e.g. GPT-4o, Claude-Sonnet) perform well across a wide range of tasks, they may incur significant financial, energy and computational costs. These costs may be"},"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":"2502.00409","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-01T12:08:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3346f9a5503784348938194d09d476f8d367d4ae38448e6ba5b1c724bd1a51b4","abstract_canon_sha256":"8d5abbb1bb598d49feed7bc032618aa9a3f0ee59c94dcf63c733eb5108805a3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:32.543687Z","signature_b64":"kHuvCPJsqK5lgu2rR2djAZygjpterPnSm/BdWdmCRmVEgvbnvmA4s/ORDA34pGp2qgl8xgxKTgHSdCewEloDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd4e1f79d3525906a59e4e1a3d5b07e83b9bf1146ad60cc14169fab0f637b4eb","last_reissued_at":"2026-07-05T11:40:32.543143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:32.543143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Antoine Gourru, Christophe Bouvard, Clovis Varangot-Reille, Fran\\c{c}ois Jacquenet, Marion Schaeffer, Mathieu Ciancone","submitted_at":"2025-02-01T12:08:38Z","abstract_excerpt":"Large Language Model (LLM)-based systems, i.e. interconnected elements that include an LLM as a central component, such as conversational agents, are usually designed with monolithic, static architectures that rely on a single, general-purpose LLM to handle all user queries. However, these systems may be inefficient as different queries may require different levels of reasoning, domain knowledge or pre-processing. While generalist LLMs (e.g. GPT-4o, Claude-Sonnet) perform well across a wide range of tasks, they may incur significant financial, energy and computational costs. These costs may be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00409","kind":"arxiv","version":3},"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/2502.00409/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":"2502.00409","created_at":"2026-07-05T11:40:32.543198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00409v3","created_at":"2026-07-05T11:40:32.543198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00409","created_at":"2026-07-05T11:40:32.543198+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVHB66OTKJMQ","created_at":"2026-07-05T11:40:32.543198+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVHB66OTKJMQNJM6","created_at":"2026-07-05T11:40:32.543198+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVHB66OT","created_at":"2026-07-05T11:40:32.543198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2606.18774","citing_title":"RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06924","citing_title":"From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing","ref_index":146,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30187","citing_title":"Modularizing Educational LLM-Agency for Fostering Responsible Learning Assistance","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18859","citing_title":"TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2505.12601","citing_title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18859","citing_title":"TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11301","citing_title":"LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02241","citing_title":"Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07805","citing_title":"Flexible Routing via Uncertainty Decomposition","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVHB66OTKJMQNJM6JYND2WYH5A","json":"https://pith.science/pith/XVHB66OTKJMQNJM6JYND2WYH5A.json","graph_json":"https://pith.science/api/pith-number/XVHB66OTKJMQNJM6JYND2WYH5A/graph.json","events_json":"https://pith.science/api/pith-number/XVHB66OTKJMQNJM6JYND2WYH5A/events.json","paper":"https://pith.science/paper/XVHB66OT"},"agent_actions":{"view_html":"https://pith.science/pith/XVHB66OTKJMQNJM6JYND2WYH5A","download_json":"https://pith.science/pith/XVHB66OTKJMQNJM6JYND2WYH5A.json","view_paper":"https://pith.science/paper/XVHB66OT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00409&json=true","fetch_graph":"https://pith.science/api/pith-number/XVHB66OTKJMQNJM6JYND2WYH5A/graph.json","fetch_events":"https://pith.science/api/pith-number/XVHB66OTKJMQNJM6JYND2WYH5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVHB66OTKJMQNJM6JYND2WYH5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVHB66OTKJMQNJM6JYND2WYH5A/action/storage_attestation","attest_author":"https://pith.science/pith/XVHB66OTKJMQNJM6JYND2WYH5A/action/author_attestation","sign_citation":"https://pith.science/pith/XVHB66OTKJMQNJM6JYND2WYH5A/action/citation_signature","submit_replication":"https://pith.science/pith/XVHB66OTKJMQNJM6JYND2WYH5A/action/replication_record"}},"created_at":"2026-07-05T11:40:32.543198+00:00","updated_at":"2026-07-05T11:40:32.543198+00:00"}