{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YMCJ5OMAGG7ZLQX2ZTSKQGKH5B","short_pith_number":"pith:YMCJ5OMA","schema_version":"1.0","canonical_sha256":"c3049eb98031bf95c2facce4a81947e86c7f8e2d05fdbc1cf7e3eae16a707daa","source":{"kind":"arxiv","id":"2401.13979","version":3},"attestation_state":"computed","paper":{"title":"Routoo: Learning to Route to Large Language Models Effectively","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alireza Mohammadshahi, Arshad Rafiq Shaikh, Majid Yazdani","submitted_at":"2024-01-25T06:45:32Z","abstract_excerpt":"LLMs with superior response quality--particularly larger or closed-source models--often come with higher inference costs, making their deployment inefficient and costly. Meanwhile, developing foundational LLMs from scratch is becoming increasingly resource-intensive and impractical for many applications. To address the challenge of balancing quality and cost, we introduce Routoo, an architecture designed to optimize the selection of LLMs for specific prompts based on performance, cost, and efficiency. Routoo provides controllability over the trade-off between inference cost and quality, enabli"},"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":"2401.13979","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-25T06:45:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ac56fa323fc06421a413c57a2e98c45df23c4b82206bb753c6418b2e7cf5cdf7","abstract_canon_sha256":"8f6e6527028c649e8841d4d16f105006a1c49d028d1fb56b3e063ea88bca3a0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:29.874861Z","signature_b64":"+fWhcWBM1v0aVXZZV1SXFvfODxiO2LkUFzWQdo0lH24fRsGwmaA0rI7XQBsjoxowMye8EewNRyp56A3Qp8gXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3049eb98031bf95c2facce4a81947e86c7f8e2d05fdbc1cf7e3eae16a707daa","last_reissued_at":"2026-07-05T09:14:29.874431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:29.874431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Routoo: Learning to Route to Large Language Models Effectively","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alireza Mohammadshahi, Arshad Rafiq Shaikh, Majid Yazdani","submitted_at":"2024-01-25T06:45:32Z","abstract_excerpt":"LLMs with superior response quality--particularly larger or closed-source models--often come with higher inference costs, making their deployment inefficient and costly. Meanwhile, developing foundational LLMs from scratch is becoming increasingly resource-intensive and impractical for many applications. To address the challenge of balancing quality and cost, we introduce Routoo, an architecture designed to optimize the selection of LLMs for specific prompts based on performance, cost, and efficiency. Routoo provides controllability over the trade-off between inference cost and quality, enabli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13979","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/2401.13979/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":"2401.13979","created_at":"2026-07-05T09:14:29.874485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13979v3","created_at":"2026-07-05T09:14:29.874485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13979","created_at":"2026-07-05T09:14:29.874485+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMCJ5OMAGG7Z","created_at":"2026-07-05T09:14:29.874485+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMCJ5OMAGG7ZLQX2","created_at":"2026-07-05T09:14:29.874485+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMCJ5OMA","created_at":"2026-07-05T09:14:29.874485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06924","citing_title":"From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18036","citing_title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12601","citing_title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24814","citing_title":"A Greedy PDE Router for Blending Neural Operators and Classical Methods","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B","json":"https://pith.science/pith/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B.json","graph_json":"https://pith.science/api/pith-number/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B/graph.json","events_json":"https://pith.science/api/pith-number/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B/events.json","paper":"https://pith.science/paper/YMCJ5OMA"},"agent_actions":{"view_html":"https://pith.science/pith/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B","download_json":"https://pith.science/pith/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B.json","view_paper":"https://pith.science/paper/YMCJ5OMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13979&json=true","fetch_graph":"https://pith.science/api/pith-number/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B/graph.json","fetch_events":"https://pith.science/api/pith-number/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B/action/storage_attestation","attest_author":"https://pith.science/pith/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B/action/author_attestation","sign_citation":"https://pith.science/pith/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B/action/citation_signature","submit_replication":"https://pith.science/pith/YMCJ5OMAGG7ZLQX2ZTSKQGKH5B/action/replication_record"}},"created_at":"2026-07-05T09:14:29.874485+00:00","updated_at":"2026-07-05T09:14:29.874485+00:00"}