{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QRDLASBSBHVI72WNYZBAJPQ5WD","short_pith_number":"pith:QRDLASBS","schema_version":"1.0","canonical_sha256":"8446b0483209ea8feacdc64204be1db0eb69b5772e930cee193c58cebb063c99","source":{"kind":"arxiv","id":"2412.04167","version":1},"attestation_state":"computed","paper":{"title":"Bench-CoE: a Framework for Collaboration of Experts from Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jinkun Zhao, Lei Huang, Peilin Feng, Shuhao Liao, Siwei Wen, Wenjun Wu, Xingjian Zhang, Yuanshuai Wang","submitted_at":"2024-12-05T14:03:41Z","abstract_excerpt":"Large Language Models (LLMs) are key technologies driving intelligent systems to handle multiple tasks. To meet the demands of various tasks, an increasing number of LLMs-driven experts with diverse capabilities have been developed, accompanied by corresponding benchmarks to evaluate their performance. This paper proposes the Bench-CoE framework, which enables Collaboration of Experts (CoE) by effectively leveraging benchmark evaluations to achieve optimal performance across various tasks. Bench-CoE includes a set of expert models, a router for assigning tasks to corresponding experts, and a b"},"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":"2412.04167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-05T14:03:41Z","cross_cats_sorted":[],"title_canon_sha256":"5cacfdd924c19941491a5ee90730846bfb9c68ef682009723e72b78939f7e7f2","abstract_canon_sha256":"6fb0944ae6d091bb2cd7dc8e08edb170dd40a89441e25c44894f0c7916a8be44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:00.338918Z","signature_b64":"Z+sxTJmH6M6KSILNamI5XIWNWrGORmYY3KCRACJP5qnc+NeeyzFiJiACYNYx5P/UIW3rMcBU1MbpHKDfeCkhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8446b0483209ea8feacdc64204be1db0eb69b5772e930cee193c58cebb063c99","last_reissued_at":"2026-07-05T09:45:00.338436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:00.338436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bench-CoE: a Framework for Collaboration of Experts from Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jinkun Zhao, Lei Huang, Peilin Feng, Shuhao Liao, Siwei Wen, Wenjun Wu, Xingjian Zhang, Yuanshuai Wang","submitted_at":"2024-12-05T14:03:41Z","abstract_excerpt":"Large Language Models (LLMs) are key technologies driving intelligent systems to handle multiple tasks. To meet the demands of various tasks, an increasing number of LLMs-driven experts with diverse capabilities have been developed, accompanied by corresponding benchmarks to evaluate their performance. This paper proposes the Bench-CoE framework, which enables Collaboration of Experts (CoE) by effectively leveraging benchmark evaluations to achieve optimal performance across various tasks. Bench-CoE includes a set of expert models, a router for assigning tasks to corresponding experts, and a b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04167","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/2412.04167/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":"2412.04167","created_at":"2026-07-05T09:45:00.338489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04167v1","created_at":"2026-07-05T09:45:00.338489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04167","created_at":"2026-07-05T09:45:00.338489+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRDLASBSBHVI","created_at":"2026-07-05T09:45:00.338489+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRDLASBSBHVI72WN","created_at":"2026-07-05T09:45:00.338489+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRDLASBS","created_at":"2026-07-05T09:45:00.338489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04378","citing_title":"DLLG: Dynamic Logit-Level Gating of LLM Experts","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18036","citing_title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRDLASBSBHVI72WNYZBAJPQ5WD","json":"https://pith.science/pith/QRDLASBSBHVI72WNYZBAJPQ5WD.json","graph_json":"https://pith.science/api/pith-number/QRDLASBSBHVI72WNYZBAJPQ5WD/graph.json","events_json":"https://pith.science/api/pith-number/QRDLASBSBHVI72WNYZBAJPQ5WD/events.json","paper":"https://pith.science/paper/QRDLASBS"},"agent_actions":{"view_html":"https://pith.science/pith/QRDLASBSBHVI72WNYZBAJPQ5WD","download_json":"https://pith.science/pith/QRDLASBSBHVI72WNYZBAJPQ5WD.json","view_paper":"https://pith.science/paper/QRDLASBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04167&json=true","fetch_graph":"https://pith.science/api/pith-number/QRDLASBSBHVI72WNYZBAJPQ5WD/graph.json","fetch_events":"https://pith.science/api/pith-number/QRDLASBSBHVI72WNYZBAJPQ5WD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRDLASBSBHVI72WNYZBAJPQ5WD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRDLASBSBHVI72WNYZBAJPQ5WD/action/storage_attestation","attest_author":"https://pith.science/pith/QRDLASBSBHVI72WNYZBAJPQ5WD/action/author_attestation","sign_citation":"https://pith.science/pith/QRDLASBSBHVI72WNYZBAJPQ5WD/action/citation_signature","submit_replication":"https://pith.science/pith/QRDLASBSBHVI72WNYZBAJPQ5WD/action/replication_record"}},"created_at":"2026-07-05T09:45:00.338489+00:00","updated_at":"2026-07-05T09:45:00.338489+00:00"}