{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XJNMAQLZOUZWOQO6FJK73KQCJU","short_pith_number":"pith:XJNMAQLZ","schema_version":"1.0","canonical_sha256":"ba5ac0417975336741de2a55fdaa024d3075bfc24230f0a2c42e6d1dd4b1a1f9","source":{"kind":"arxiv","id":"2409.19886","version":1},"attestation_state":"computed","paper":{"title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Baijiong Lin, James T. Kwok, Shuhao Chen, Weisen Jiang, Yu Zhang","submitted_at":"2024-09-30T02:31:40Z","abstract_excerpt":"Recent works show that assembling multiple off-the-shelf large language models (LLMs) can harness their complementary abilities. To achieve this, routing is a promising method, which learns a router to select the most suitable LLM for each query. However, existing routing models are ineffective when multiple LLMs perform well for a query. To address this problem, in this paper, we propose a method called query-based Router by Dual Contrastive learning (RouterDC). The RouterDC model consists of an encoder and LLM embeddings, and we propose two contrastive learning losses to train the RouterDC m"},"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":"2409.19886","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T02:31:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ff379953df70492c56e555f8f8b3d36e9571e9229af3980e8a6f8ac4c2e6fd96","abstract_canon_sha256":"98d99cf740d85b429e47a8bd672134c6aa732f350fd0ffc35c4215f8dff59e66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:24.331100Z","signature_b64":"iFy/bBflMCIalNdJswfrB6V/5DSVBbucyZyUv+62pC8iS52eGLI4gKOkBXDQAi+wE+5mjiBI7JDHcOCvqtL4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba5ac0417975336741de2a55fdaa024d3075bfc24230f0a2c42e6d1dd4b1a1f9","last_reissued_at":"2026-07-05T09:13:24.330678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:24.330678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Baijiong Lin, James T. Kwok, Shuhao Chen, Weisen Jiang, Yu Zhang","submitted_at":"2024-09-30T02:31:40Z","abstract_excerpt":"Recent works show that assembling multiple off-the-shelf large language models (LLMs) can harness their complementary abilities. To achieve this, routing is a promising method, which learns a router to select the most suitable LLM for each query. However, existing routing models are ineffective when multiple LLMs perform well for a query. To address this problem, in this paper, we propose a method called query-based Router by Dual Contrastive learning (RouterDC). The RouterDC model consists of an encoder and LLM embeddings, and we propose two contrastive learning losses to train the RouterDC m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19886","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/2409.19886/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":"2409.19886","created_at":"2026-07-05T09:13:24.330739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19886v1","created_at":"2026-07-05T09:13:24.330739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19886","created_at":"2026-07-05T09:13:24.330739+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJNMAQLZOUZW","created_at":"2026-07-05T09:13:24.330739+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJNMAQLZOUZWOQO6","created_at":"2026-07-05T09:13:24.330739+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJNMAQLZ","created_at":"2026-07-05T09:13:24.330739+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17628","citing_title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","ref_index":154,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07587","citing_title":"The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJNMAQLZOUZWOQO6FJK73KQCJU","json":"https://pith.science/pith/XJNMAQLZOUZWOQO6FJK73KQCJU.json","graph_json":"https://pith.science/api/pith-number/XJNMAQLZOUZWOQO6FJK73KQCJU/graph.json","events_json":"https://pith.science/api/pith-number/XJNMAQLZOUZWOQO6FJK73KQCJU/events.json","paper":"https://pith.science/paper/XJNMAQLZ"},"agent_actions":{"view_html":"https://pith.science/pith/XJNMAQLZOUZWOQO6FJK73KQCJU","download_json":"https://pith.science/pith/XJNMAQLZOUZWOQO6FJK73KQCJU.json","view_paper":"https://pith.science/paper/XJNMAQLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19886&json=true","fetch_graph":"https://pith.science/api/pith-number/XJNMAQLZOUZWOQO6FJK73KQCJU/graph.json","fetch_events":"https://pith.science/api/pith-number/XJNMAQLZOUZWOQO6FJK73KQCJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJNMAQLZOUZWOQO6FJK73KQCJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJNMAQLZOUZWOQO6FJK73KQCJU/action/storage_attestation","attest_author":"https://pith.science/pith/XJNMAQLZOUZWOQO6FJK73KQCJU/action/author_attestation","sign_citation":"https://pith.science/pith/XJNMAQLZOUZWOQO6FJK73KQCJU/action/citation_signature","submit_replication":"https://pith.science/pith/XJNMAQLZOUZWOQO6FJK73KQCJU/action/replication_record"}},"created_at":"2026-07-05T09:13:24.330739+00:00","updated_at":"2026-07-05T09:13:24.330739+00:00"}