{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O5ZUJIZNZBCUO4RBYYYCN6OG4Q","short_pith_number":"pith:O5ZUJIZN","schema_version":"1.0","canonical_sha256":"777344a32dc845477221c63026f9c6e409c3a8fc10fcada16a44bd0b97e484d0","source":{"kind":"arxiv","id":"2502.11021","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Uncertainty Estimation for Efficient LLM Routing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.NI","authors_text":"Asal Mehradfar, Dimitrios Dimitriadis, Salman Avestimehr, Tuo Zhang","submitted_at":"2025-02-16T07:08:47Z","abstract_excerpt":"Deploying large language models (LLMs) in edge-cloud environments requires an efficient routing strategy to balance cost and response quality. Traditional approaches prioritize either human-preference data or accuracy metrics from benchmark datasets as routing criteria, but these methods suffer from rigidity and subjectivity. Moreover, existing routing frameworks primarily focus on accuracy and cost, neglecting response quality from a human preference perspective. In this work, we propose the Confidence-Driven LLM Router, a novel framework that leverages uncertainty estimation to optimize rout"},"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":"2502.11021","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2025-02-16T07:08:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0288952662566dec2967d1c9774bc3f8c732e90d6e1ee926cc055af180a8844a","abstract_canon_sha256":"a96df99460bdd1e3e6ef91429553f1153659192421e8f3c52df5ff983b749525"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:02.506664Z","signature_b64":"uhudRA5VQmrwnlkNuW2rrVomiRC5lHlZjIlZNLufQOv1G2jRSed9GW7GNXmkkbKdrvfX7k7+B1Sz3YQ+VZhBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"777344a32dc845477221c63026f9c6e409c3a8fc10fcada16a44bd0b97e484d0","last_reissued_at":"2026-07-05T10:15:02.506175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:02.506175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Uncertainty Estimation for Efficient LLM Routing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.NI","authors_text":"Asal Mehradfar, Dimitrios Dimitriadis, Salman Avestimehr, Tuo Zhang","submitted_at":"2025-02-16T07:08:47Z","abstract_excerpt":"Deploying large language models (LLMs) in edge-cloud environments requires an efficient routing strategy to balance cost and response quality. Traditional approaches prioritize either human-preference data or accuracy metrics from benchmark datasets as routing criteria, but these methods suffer from rigidity and subjectivity. Moreover, existing routing frameworks primarily focus on accuracy and cost, neglecting response quality from a human preference perspective. In this work, we propose the Confidence-Driven LLM Router, a novel framework that leverages uncertainty estimation to optimize rout"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11021","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/2502.11021/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":"2502.11021","created_at":"2026-07-05T10:15:02.506232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11021v1","created_at":"2026-07-05T10:15:02.506232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11021","created_at":"2026-07-05T10:15:02.506232+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5ZUJIZNZBCU","created_at":"2026-07-05T10:15:02.506232+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5ZUJIZNZBCUO4RB","created_at":"2026-07-05T10:15:02.506232+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5ZUJIZN","created_at":"2026-07-05T10:15:02.506232+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":121,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11301","citing_title":"LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25591","citing_title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02241","citing_title":"Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O5ZUJIZNZBCUO4RBYYYCN6OG4Q","json":"https://pith.science/pith/O5ZUJIZNZBCUO4RBYYYCN6OG4Q.json","graph_json":"https://pith.science/api/pith-number/O5ZUJIZNZBCUO4RBYYYCN6OG4Q/graph.json","events_json":"https://pith.science/api/pith-number/O5ZUJIZNZBCUO4RBYYYCN6OG4Q/events.json","paper":"https://pith.science/paper/O5ZUJIZN"},"agent_actions":{"view_html":"https://pith.science/pith/O5ZUJIZNZBCUO4RBYYYCN6OG4Q","download_json":"https://pith.science/pith/O5ZUJIZNZBCUO4RBYYYCN6OG4Q.json","view_paper":"https://pith.science/paper/O5ZUJIZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11021&json=true","fetch_graph":"https://pith.science/api/pith-number/O5ZUJIZNZBCUO4RBYYYCN6OG4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/O5ZUJIZNZBCUO4RBYYYCN6OG4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5ZUJIZNZBCUO4RBYYYCN6OG4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5ZUJIZNZBCUO4RBYYYCN6OG4Q/action/storage_attestation","attest_author":"https://pith.science/pith/O5ZUJIZNZBCUO4RBYYYCN6OG4Q/action/author_attestation","sign_citation":"https://pith.science/pith/O5ZUJIZNZBCUO4RBYYYCN6OG4Q/action/citation_signature","submit_replication":"https://pith.science/pith/O5ZUJIZNZBCUO4RBYYYCN6OG4Q/action/replication_record"}},"created_at":"2026-07-05T10:15:02.506232+00:00","updated_at":"2026-07-05T10:15:02.506232+00:00"}