{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TIIK433VIVZFEWDMS7DEJOV4FK","short_pith_number":"pith:TIIK433V","schema_version":"1.0","canonical_sha256":"9a10ae6f75457252586c97c644babc2aad2f80648d355ba007a7c991acffd506","source":{"kind":"arxiv","id":"2409.02685","version":2},"attestation_state":"computed","paper":{"title":"RouterRetriever: Routing over a Mixture of Expert Embedding Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Arman Cohan, Hyunji Lee, Kyle Lo, Luca Soldaini, Minjoon Seo","submitted_at":"2024-09-04T13:16:55Z","abstract_excerpt":"Information retrieval methods often rely on a single embedding model trained on large, general-domain datasets like MSMARCO. While this approach can produce a retriever with reasonable overall performance, they often underperform models trained on domain-specific data when testing on their respective domains. Prior work in information retrieval has tackled this through multi-task training, but the idea of routing over a mixture of domain-specific expert retrievers remains unexplored despite the popularity of such ideas in language model generation research. In this work, we introduce RouterRet"},"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":"2409.02685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-09-04T13:16:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80cb71aca7353c246773edbe14b038f700ebcd4bd11f7bbf9cebcdefb78f7925","abstract_canon_sha256":"f9884fd6b0feaea9997208c9f178887d749843fde072912cdd23a79669886c4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:14.930199Z","signature_b64":"qC7L+E5MjKr7gYXA3bZhzypZRmCo4HvBUWPNky1OsU+FfgIzUwCYJQTkw/3XCKGnE845SjuUYC7jJdorz2QTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a10ae6f75457252586c97c644babc2aad2f80648d355ba007a7c991acffd506","last_reissued_at":"2026-07-05T10:20:14.929663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:14.929663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RouterRetriever: Routing over a Mixture of Expert Embedding Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Arman Cohan, Hyunji Lee, Kyle Lo, Luca Soldaini, Minjoon Seo","submitted_at":"2024-09-04T13:16:55Z","abstract_excerpt":"Information retrieval methods often rely on a single embedding model trained on large, general-domain datasets like MSMARCO. While this approach can produce a retriever with reasonable overall performance, they often underperform models trained on domain-specific data when testing on their respective domains. Prior work in information retrieval has tackled this through multi-task training, but the idea of routing over a mixture of domain-specific expert retrievers remains unexplored despite the popularity of such ideas in language model generation research. In this work, we introduce RouterRet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02685","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/2409.02685/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":"2409.02685","created_at":"2026-07-05T10:20:14.929721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02685v2","created_at":"2026-07-05T10:20:14.929721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02685","created_at":"2026-07-05T10:20:14.929721+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIIK433VIVZF","created_at":"2026-07-05T10:20:14.929721+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIIK433VIVZFEWDM","created_at":"2026-07-05T10:20:14.929721+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIIK433V","created_at":"2026-07-05T10:20:14.929721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.13743","citing_title":"LTRR: Learning To Rank Retrievers for LLMs","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIIK433VIVZFEWDMS7DEJOV4FK","json":"https://pith.science/pith/TIIK433VIVZFEWDMS7DEJOV4FK.json","graph_json":"https://pith.science/api/pith-number/TIIK433VIVZFEWDMS7DEJOV4FK/graph.json","events_json":"https://pith.science/api/pith-number/TIIK433VIVZFEWDMS7DEJOV4FK/events.json","paper":"https://pith.science/paper/TIIK433V"},"agent_actions":{"view_html":"https://pith.science/pith/TIIK433VIVZFEWDMS7DEJOV4FK","download_json":"https://pith.science/pith/TIIK433VIVZFEWDMS7DEJOV4FK.json","view_paper":"https://pith.science/paper/TIIK433V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02685&json=true","fetch_graph":"https://pith.science/api/pith-number/TIIK433VIVZFEWDMS7DEJOV4FK/graph.json","fetch_events":"https://pith.science/api/pith-number/TIIK433VIVZFEWDMS7DEJOV4FK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIIK433VIVZFEWDMS7DEJOV4FK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIIK433VIVZFEWDMS7DEJOV4FK/action/storage_attestation","attest_author":"https://pith.science/pith/TIIK433VIVZFEWDMS7DEJOV4FK/action/author_attestation","sign_citation":"https://pith.science/pith/TIIK433VIVZFEWDMS7DEJOV4FK/action/citation_signature","submit_replication":"https://pith.science/pith/TIIK433VIVZFEWDMS7DEJOV4FK/action/replication_record"}},"created_at":"2026-07-05T10:20:14.929721+00:00","updated_at":"2026-07-05T10:20:14.929721+00:00"}