{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AW4MW3H6SMWVGT7LSCM6DAMMME","short_pith_number":"pith:AW4MW3H6","schema_version":"1.0","canonical_sha256":"05b8cb6cfe932d534feb9099e1818c6136ad7813acef0d43c7b8250cb3b6f887","source":{"kind":"arxiv","id":"2503.10657","version":2},"attestation_state":"computed","paper":{"title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guoming Ling, Hefeng Wu, Liang Lin, Shanshan Zhong, Yandong Chen, Yupei Lin, Zhongzhan Huang","submitted_at":"2025-03-08T04:07:07Z","abstract_excerpt":"Routing large language models (LLMs) is a new paradigm that uses a router to recommend the best LLM from a pool of candidates for a given input. In this paper, our comprehensive analysis with more than 8,500 LLMs reveals a novel model-level scaling up phenomenon in Routing LLMs, i.e., a capable router can significantly enhance the performance of this paradigm as the number of candidates increases. This improvement can even surpass the performance of the best single model in the pool and many existing strong LLMs, confirming it a highly promising paradigm. However, the lack of comprehensive and"},"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":"2503.10657","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-08T04:07:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c9233a380800667ef1609c44ab573e8b42b7976b1b52afdda0258eefd6208d3","abstract_canon_sha256":"a372ffc8a635f26e2928bd1735865c307faada43fbe6ece0bc11471f9dc7dbb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:41.534274Z","signature_b64":"7xxX5x5+kwYI2DKSfQbtyIC9acbSuTMWYRpSOkKOU+NqYCanplZ3gwUVNuZndPudiMDF/AspaoZ7Usu3WUAkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05b8cb6cfe932d534feb9099e1818c6136ad7813acef0d43c7b8250cb3b6f887","last_reissued_at":"2026-07-05T11:05:41.533796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:41.533796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guoming Ling, Hefeng Wu, Liang Lin, Shanshan Zhong, Yandong Chen, Yupei Lin, Zhongzhan Huang","submitted_at":"2025-03-08T04:07:07Z","abstract_excerpt":"Routing large language models (LLMs) is a new paradigm that uses a router to recommend the best LLM from a pool of candidates for a given input. In this paper, our comprehensive analysis with more than 8,500 LLMs reveals a novel model-level scaling up phenomenon in Routing LLMs, i.e., a capable router can significantly enhance the performance of this paradigm as the number of candidates increases. This improvement can even surpass the performance of the best single model in the pool and many existing strong LLMs, confirming it a highly promising paradigm. However, the lack of comprehensive and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10657","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/2503.10657/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":"2503.10657","created_at":"2026-07-05T11:05:41.533856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10657v2","created_at":"2026-07-05T11:05:41.533856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10657","created_at":"2026-07-05T11:05:41.533856+00:00"},{"alias_kind":"pith_short_12","alias_value":"AW4MW3H6SMWV","created_at":"2026-07-05T11:05:41.533856+00:00"},{"alias_kind":"pith_short_16","alias_value":"AW4MW3H6SMWVGT7L","created_at":"2026-07-05T11:05:41.533856+00:00"},{"alias_kind":"pith_short_8","alias_value":"AW4MW3H6","created_at":"2026-07-05T11:05:41.533856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08665","citing_title":"Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00053","citing_title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25424","citing_title":"SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24814","citing_title":"A Greedy PDE Router for Blending Neural Operators and Classical Methods","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07075","citing_title":"ModelLens: Finding the Best for Your Task from Myriads of Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06296","citing_title":"AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AW4MW3H6SMWVGT7LSCM6DAMMME","json":"https://pith.science/pith/AW4MW3H6SMWVGT7LSCM6DAMMME.json","graph_json":"https://pith.science/api/pith-number/AW4MW3H6SMWVGT7LSCM6DAMMME/graph.json","events_json":"https://pith.science/api/pith-number/AW4MW3H6SMWVGT7LSCM6DAMMME/events.json","paper":"https://pith.science/paper/AW4MW3H6"},"agent_actions":{"view_html":"https://pith.science/pith/AW4MW3H6SMWVGT7LSCM6DAMMME","download_json":"https://pith.science/pith/AW4MW3H6SMWVGT7LSCM6DAMMME.json","view_paper":"https://pith.science/paper/AW4MW3H6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10657&json=true","fetch_graph":"https://pith.science/api/pith-number/AW4MW3H6SMWVGT7LSCM6DAMMME/graph.json","fetch_events":"https://pith.science/api/pith-number/AW4MW3H6SMWVGT7LSCM6DAMMME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AW4MW3H6SMWVGT7LSCM6DAMMME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AW4MW3H6SMWVGT7LSCM6DAMMME/action/storage_attestation","attest_author":"https://pith.science/pith/AW4MW3H6SMWVGT7LSCM6DAMMME/action/author_attestation","sign_citation":"https://pith.science/pith/AW4MW3H6SMWVGT7LSCM6DAMMME/action/citation_signature","submit_replication":"https://pith.science/pith/AW4MW3H6SMWVGT7LSCM6DAMMME/action/replication_record"}},"created_at":"2026-07-05T11:05:41.533856+00:00","updated_at":"2026-07-05T11:05:41.533856+00:00"}