{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GGT2BZSNRJKKW67QKHF6GCFPKC","short_pith_number":"pith:GGT2BZSN","schema_version":"1.0","canonical_sha256":"31a7a0e64d8a54ab7bf051cbe308af50ac4ca24f2ac4f05c0bf948fb3a45b57f","source":{"kind":"arxiv","id":"2310.01542","version":2},"attestation_state":"computed","paper":{"title":"Fusing Models with Complementary Expertise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Xing, Felipe Maia Polo, Hongyi Wang, Mikhail Yurochkin, Souvik Kundu, Yuekai Sun","submitted_at":"2023-10-02T18:31:35Z","abstract_excerpt":"Training AI models that generalize across tasks and domains has long been among the open problems driving AI research. The emergence of Foundation Models made it easier to obtain expert models for a given task, but the heterogeneity of data that may be encountered at test time often means that any single expert is insufficient. We consider the Fusion of Experts (FoE) problem of fusing outputs of expert models with complementary knowledge of the data distribution and formulate it as an instance of supervised learning. Our method is applicable to both discriminative and generative tasks and lead"},"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":"2310.01542","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T18:31:35Z","cross_cats_sorted":[],"title_canon_sha256":"2857bacc8930a5152d0882fbe17b49076f412d9c299bdc566b57fceb1e17ce5c","abstract_canon_sha256":"c606b8343c3f509dc7b5ac822707212117bd06adfc06856a3f6acfa6b1664ff5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:10.979914Z","signature_b64":"9uctDBvCvC+zJQLNnNZR97oPV7AuTj/uDnHZQRG6I3mf3ndCSBuuk3B6Fpigs10muaBN7yxAxad5TbcKVmimBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31a7a0e64d8a54ab7bf051cbe308af50ac4ca24f2ac4f05c0bf948fb3a45b57f","last_reissued_at":"2026-07-05T08:17:10.979489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:10.979489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fusing Models with Complementary Expertise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Xing, Felipe Maia Polo, Hongyi Wang, Mikhail Yurochkin, Souvik Kundu, Yuekai Sun","submitted_at":"2023-10-02T18:31:35Z","abstract_excerpt":"Training AI models that generalize across tasks and domains has long been among the open problems driving AI research. The emergence of Foundation Models made it easier to obtain expert models for a given task, but the heterogeneity of data that may be encountered at test time often means that any single expert is insufficient. We consider the Fusion of Experts (FoE) problem of fusing outputs of expert models with complementary knowledge of the data distribution and formulate it as an instance of supervised learning. Our method is applicable to both discriminative and generative tasks and lead"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01542","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/2310.01542/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":"2310.01542","created_at":"2026-07-05T08:17:10.979547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01542v2","created_at":"2026-07-05T08:17:10.979547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01542","created_at":"2026-07-05T08:17:10.979547+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGT2BZSNRJKK","created_at":"2026-07-05T08:17:10.979547+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGT2BZSNRJKKW67Q","created_at":"2026-07-05T08:17:10.979547+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGT2BZSN","created_at":"2026-07-05T08:17:10.979547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25476","citing_title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20295","citing_title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00053","citing_title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12601","citing_title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGT2BZSNRJKKW67QKHF6GCFPKC","json":"https://pith.science/pith/GGT2BZSNRJKKW67QKHF6GCFPKC.json","graph_json":"https://pith.science/api/pith-number/GGT2BZSNRJKKW67QKHF6GCFPKC/graph.json","events_json":"https://pith.science/api/pith-number/GGT2BZSNRJKKW67QKHF6GCFPKC/events.json","paper":"https://pith.science/paper/GGT2BZSN"},"agent_actions":{"view_html":"https://pith.science/pith/GGT2BZSNRJKKW67QKHF6GCFPKC","download_json":"https://pith.science/pith/GGT2BZSNRJKKW67QKHF6GCFPKC.json","view_paper":"https://pith.science/paper/GGT2BZSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01542&json=true","fetch_graph":"https://pith.science/api/pith-number/GGT2BZSNRJKKW67QKHF6GCFPKC/graph.json","fetch_events":"https://pith.science/api/pith-number/GGT2BZSNRJKKW67QKHF6GCFPKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGT2BZSNRJKKW67QKHF6GCFPKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGT2BZSNRJKKW67QKHF6GCFPKC/action/storage_attestation","attest_author":"https://pith.science/pith/GGT2BZSNRJKKW67QKHF6GCFPKC/action/author_attestation","sign_citation":"https://pith.science/pith/GGT2BZSNRJKKW67QKHF6GCFPKC/action/citation_signature","submit_replication":"https://pith.science/pith/GGT2BZSNRJKKW67QKHF6GCFPKC/action/replication_record"}},"created_at":"2026-07-05T08:17:10.979547+00:00","updated_at":"2026-07-05T08:17:10.979547+00:00"}