{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T45ZQ42GO4JNMLBMEECDFYFLW7","short_pith_number":"pith:T45ZQ42G","schema_version":"1.0","canonical_sha256":"9f3b9873467712d62c2c210432e0abb7d518da20f40c19cd42d1ff2ff48bc24e","source":{"kind":"arxiv","id":"2407.00487","version":3},"attestation_state":"computed","paper":{"title":"It's Morphing Time: Unleashing the Potential of Multiple LLMs via Multi-objective Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aimin Zhou, Bingdong Li, Hao Hao, Hong Qian, Ke Tang, Peng Yang, Yanting Yang, Zixiang Di","submitted_at":"2024-06-29T16:34:23Z","abstract_excerpt":"In this paper, we introduce a novel approach for addressing the multi-objective optimization problem in large language model merging via black-box multi-objective optimization algorithms. The goal of model merging is to combine multiple models, each excelling in different tasks, into a single model that outperforms any of the individual source models. However, model merging faces two significant challenges: First, existing methods rely heavily on human knowledge or intuition. Second, it's difficult to obtain the great model merging configuration in limited evaluations. To address these challen"},"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":"2407.00487","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T16:34:23Z","cross_cats_sorted":[],"title_canon_sha256":"c71e9b0d0534a3f83261e8281d66226648c5946e893c732ae1d4e085b28c2069","abstract_canon_sha256":"09e3eaae813a94e57cc0407d6475e0aa974cb24825366bd9f708a54853e9ccea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:24.485416Z","signature_b64":"coQ33vCHlT8LUqcIkujtqAWJjKiqld8EMe9fvaF32nyXS1214wUgvjz4JgQNFVV5IMKsSxSiwanAMNKZRf5dCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f3b9873467712d62c2c210432e0abb7d518da20f40c19cd42d1ff2ff48bc24e","last_reissued_at":"2026-07-05T09:39:24.484902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:24.484902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"It's Morphing Time: Unleashing the Potential of Multiple LLMs via Multi-objective Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aimin Zhou, Bingdong Li, Hao Hao, Hong Qian, Ke Tang, Peng Yang, Yanting Yang, Zixiang Di","submitted_at":"2024-06-29T16:34:23Z","abstract_excerpt":"In this paper, we introduce a novel approach for addressing the multi-objective optimization problem in large language model merging via black-box multi-objective optimization algorithms. The goal of model merging is to combine multiple models, each excelling in different tasks, into a single model that outperforms any of the individual source models. However, model merging faces two significant challenges: First, existing methods rely heavily on human knowledge or intuition. Second, it's difficult to obtain the great model merging configuration in limited evaluations. To address these challen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00487","kind":"arxiv","version":3},"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/2407.00487/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":"2407.00487","created_at":"2026-07-05T09:39:24.484959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00487v3","created_at":"2026-07-05T09:39:24.484959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00487","created_at":"2026-07-05T09:39:24.484959+00:00"},{"alias_kind":"pith_short_12","alias_value":"T45ZQ42GO4JN","created_at":"2026-07-05T09:39:24.484959+00:00"},{"alias_kind":"pith_short_16","alias_value":"T45ZQ42GO4JNMLBM","created_at":"2026-07-05T09:39:24.484959+00:00"},{"alias_kind":"pith_short_8","alias_value":"T45ZQ42G","created_at":"2026-07-05T09:39:24.484959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.07666","citing_title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","ref_index":116,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T45ZQ42GO4JNMLBMEECDFYFLW7","json":"https://pith.science/pith/T45ZQ42GO4JNMLBMEECDFYFLW7.json","graph_json":"https://pith.science/api/pith-number/T45ZQ42GO4JNMLBMEECDFYFLW7/graph.json","events_json":"https://pith.science/api/pith-number/T45ZQ42GO4JNMLBMEECDFYFLW7/events.json","paper":"https://pith.science/paper/T45ZQ42G"},"agent_actions":{"view_html":"https://pith.science/pith/T45ZQ42GO4JNMLBMEECDFYFLW7","download_json":"https://pith.science/pith/T45ZQ42GO4JNMLBMEECDFYFLW7.json","view_paper":"https://pith.science/paper/T45ZQ42G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00487&json=true","fetch_graph":"https://pith.science/api/pith-number/T45ZQ42GO4JNMLBMEECDFYFLW7/graph.json","fetch_events":"https://pith.science/api/pith-number/T45ZQ42GO4JNMLBMEECDFYFLW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T45ZQ42GO4JNMLBMEECDFYFLW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T45ZQ42GO4JNMLBMEECDFYFLW7/action/storage_attestation","attest_author":"https://pith.science/pith/T45ZQ42GO4JNMLBMEECDFYFLW7/action/author_attestation","sign_citation":"https://pith.science/pith/T45ZQ42GO4JNMLBMEECDFYFLW7/action/citation_signature","submit_replication":"https://pith.science/pith/T45ZQ42GO4JNMLBMEECDFYFLW7/action/replication_record"}},"created_at":"2026-07-05T09:39:24.484959+00:00","updated_at":"2026-07-05T09:39:24.484959+00:00"}