{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SD2VPFYESBOM3C2CS2ILBX55ND","short_pith_number":"pith:SD2VPFYE","schema_version":"1.0","canonical_sha256":"90f5579704905ccd8b429690b0dfbd68c6f0ed28c15a8c2f711f98b8f4f7603a","source":{"kind":"arxiv","id":"2406.09770","version":1},"attestation_state":"computed","paper":{"title":"Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anke Tang, Bo Du, Han Hu, Li Shen, Shiwei Liu, Yong Luo","submitted_at":"2024-06-14T07:16:18Z","abstract_excerpt":"Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost of training and evaluating models. Efficient Pareto front approximation of large models enables multi-objective optimization for various tasks such as multi-task learning and trade-off analysis. Existing algorithms for learning Pareto set, including (1) evolutionary, hypernetworks, and hypervolume-maximization methods, are computationally expensive and have restricted scalability to large models; (2) Scalarization al"},"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":"2406.09770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T07:16:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c808d33a220dea05a0dbd8f142f61beb5073137dea18f4159d0a819cfcd00aa2","abstract_canon_sha256":"a1edbd5b4dee922ae3dd286ef1018841d504b6fe33bd930d2c9f1445f4b3f0b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:59.627687Z","signature_b64":"+OzPQIz4hHEHQZOz9wK9fewVA1epAjhPOWR0ipV6H7/eKDR3NzbyKFuZLZsAxCl2Fac3RGsqZEKM/TKe3MXOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90f5579704905ccd8b429690b0dfbd68c6f0ed28c15a8c2f711f98b8f4f7603a","last_reissued_at":"2026-07-05T08:31:59.627162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:59.627162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anke Tang, Bo Du, Han Hu, Li Shen, Shiwei Liu, Yong Luo","submitted_at":"2024-06-14T07:16:18Z","abstract_excerpt":"Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost of training and evaluating models. Efficient Pareto front approximation of large models enables multi-objective optimization for various tasks such as multi-task learning and trade-off analysis. Existing algorithms for learning Pareto set, including (1) evolutionary, hypernetworks, and hypervolume-maximization methods, are computationally expensive and have restricted scalability to large models; (2) Scalarization al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09770","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/2406.09770/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":"2406.09770","created_at":"2026-07-05T08:31:59.627231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09770v1","created_at":"2026-07-05T08:31:59.627231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09770","created_at":"2026-07-05T08:31:59.627231+00:00"},{"alias_kind":"pith_short_12","alias_value":"SD2VPFYESBOM","created_at":"2026-07-05T08:31:59.627231+00:00"},{"alias_kind":"pith_short_16","alias_value":"SD2VPFYESBOM3C2C","created_at":"2026-07-05T08:31:59.627231+00:00"},{"alias_kind":"pith_short_8","alias_value":"SD2VPFYE","created_at":"2026-07-05T08:31:59.627231+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":208,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SD2VPFYESBOM3C2CS2ILBX55ND","json":"https://pith.science/pith/SD2VPFYESBOM3C2CS2ILBX55ND.json","graph_json":"https://pith.science/api/pith-number/SD2VPFYESBOM3C2CS2ILBX55ND/graph.json","events_json":"https://pith.science/api/pith-number/SD2VPFYESBOM3C2CS2ILBX55ND/events.json","paper":"https://pith.science/paper/SD2VPFYE"},"agent_actions":{"view_html":"https://pith.science/pith/SD2VPFYESBOM3C2CS2ILBX55ND","download_json":"https://pith.science/pith/SD2VPFYESBOM3C2CS2ILBX55ND.json","view_paper":"https://pith.science/paper/SD2VPFYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09770&json=true","fetch_graph":"https://pith.science/api/pith-number/SD2VPFYESBOM3C2CS2ILBX55ND/graph.json","fetch_events":"https://pith.science/api/pith-number/SD2VPFYESBOM3C2CS2ILBX55ND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SD2VPFYESBOM3C2CS2ILBX55ND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SD2VPFYESBOM3C2CS2ILBX55ND/action/storage_attestation","attest_author":"https://pith.science/pith/SD2VPFYESBOM3C2CS2ILBX55ND/action/author_attestation","sign_citation":"https://pith.science/pith/SD2VPFYESBOM3C2CS2ILBX55ND/action/citation_signature","submit_replication":"https://pith.science/pith/SD2VPFYESBOM3C2CS2ILBX55ND/action/replication_record"}},"created_at":"2026-07-05T08:31:59.627231+00:00","updated_at":"2026-07-05T08:31:59.627231+00:00"}