{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DGBKXHSPQNZ2FGXEPYIUUSOSD7","short_pith_number":"pith:DGBKXHSP","schema_version":"1.0","canonical_sha256":"1982ab9e4f8373a29ae47e114a49d21fe22075e546c08e00358a6075c5e86b5f","source":{"kind":"arxiv","id":"2505.22694","version":1},"attestation_state":"computed","paper":{"title":"MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dacao Zhang, Kun Zhang, Le Wu, Shimao Chu, Si Wei, Xin Li","submitted_at":"2025-05-28T12:32:09Z","abstract_excerpt":"With the rapid development of Large Language Models (LLMs), Parameter-Efficient Fine-Tuning (PEFT) methods have gained significant attention, which aims to achieve efficient fine-tuning of LLMs with fewer parameters. As a representative PEFT method, Low-Rank Adaptation (LoRA) introduces low-rank matrices to approximate the incremental tuning parameters and achieves impressive performance over multiple scenarios. After that, plenty of improvements have been proposed for further improvement. However, these methods either focus on single-task scenarios or separately train multiple LoRA modules fo"},"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":"2505.22694","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T12:32:09Z","cross_cats_sorted":[],"title_canon_sha256":"fae7d1d9c3c095c96e5f76d58270af3b804dec23a52a7cba7e5c802686510636","abstract_canon_sha256":"c2625577efdb02ee60479b8e17ad99841277cb9544e78e6b507bdc10576c7162"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:48.765096Z","signature_b64":"0ZRnVqy3x0DHDisbQgS1sJW80epSxa6MoE06CcfplreScTPl1A0RRpkY9AMHzi10OUm0yCYjL0pMwegNQlKDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1982ab9e4f8373a29ae47e114a49d21fe22075e546c08e00358a6075c5e86b5f","last_reissued_at":"2026-07-05T11:11:48.764606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:48.764606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dacao Zhang, Kun Zhang, Le Wu, Shimao Chu, Si Wei, Xin Li","submitted_at":"2025-05-28T12:32:09Z","abstract_excerpt":"With the rapid development of Large Language Models (LLMs), Parameter-Efficient Fine-Tuning (PEFT) methods have gained significant attention, which aims to achieve efficient fine-tuning of LLMs with fewer parameters. As a representative PEFT method, Low-Rank Adaptation (LoRA) introduces low-rank matrices to approximate the incremental tuning parameters and achieves impressive performance over multiple scenarios. After that, plenty of improvements have been proposed for further improvement. However, these methods either focus on single-task scenarios or separately train multiple LoRA modules fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22694","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/2505.22694/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":"2505.22694","created_at":"2026-07-05T11:11:48.764666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22694v1","created_at":"2026-07-05T11:11:48.764666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22694","created_at":"2026-07-05T11:11:48.764666+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGBKXHSPQNZ2","created_at":"2026-07-05T11:11:48.764666+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGBKXHSPQNZ2FGXE","created_at":"2026-07-05T11:11:48.764666+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGBKXHSP","created_at":"2026-07-05T11:11:48.764666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13161","citing_title":"A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25414","citing_title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13161","citing_title":"A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19042","citing_title":"STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGBKXHSPQNZ2FGXEPYIUUSOSD7","json":"https://pith.science/pith/DGBKXHSPQNZ2FGXEPYIUUSOSD7.json","graph_json":"https://pith.science/api/pith-number/DGBKXHSPQNZ2FGXEPYIUUSOSD7/graph.json","events_json":"https://pith.science/api/pith-number/DGBKXHSPQNZ2FGXEPYIUUSOSD7/events.json","paper":"https://pith.science/paper/DGBKXHSP"},"agent_actions":{"view_html":"https://pith.science/pith/DGBKXHSPQNZ2FGXEPYIUUSOSD7","download_json":"https://pith.science/pith/DGBKXHSPQNZ2FGXEPYIUUSOSD7.json","view_paper":"https://pith.science/paper/DGBKXHSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22694&json=true","fetch_graph":"https://pith.science/api/pith-number/DGBKXHSPQNZ2FGXEPYIUUSOSD7/graph.json","fetch_events":"https://pith.science/api/pith-number/DGBKXHSPQNZ2FGXEPYIUUSOSD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGBKXHSPQNZ2FGXEPYIUUSOSD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGBKXHSPQNZ2FGXEPYIUUSOSD7/action/storage_attestation","attest_author":"https://pith.science/pith/DGBKXHSPQNZ2FGXEPYIUUSOSD7/action/author_attestation","sign_citation":"https://pith.science/pith/DGBKXHSPQNZ2FGXEPYIUUSOSD7/action/citation_signature","submit_replication":"https://pith.science/pith/DGBKXHSPQNZ2FGXEPYIUUSOSD7/action/replication_record"}},"created_at":"2026-07-05T11:11:48.764666+00:00","updated_at":"2026-07-05T11:11:48.764666+00:00"}