{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WB3WFHFZ27P7WKUDJ6SGGDNN65","short_pith_number":"pith:WB3WFHFZ","schema_version":"1.0","canonical_sha256":"b077629cb9d7dffb2a834fa4630dadf75cc6ff69300fccbb28bda9a50af792c8","source":{"kind":"arxiv","id":"2505.06272","version":1},"attestation_state":"computed","paper":{"title":"A Sensitivity-Driven Expert Allocation Method in LoRA-MoE for Efficient Fine-Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boyu Diao, Junzhou Xu","submitted_at":"2025-05-06T13:22:46Z","abstract_excerpt":"As deep learning models expand, the pre-training-fine-tuning paradigm has become the standard approach for handling various downstream tasks. However, shared parameters can lead to diminished performance when dealing with complex datasets involving multiple tasks. While introducing Mixture-of-Experts (MoE) methods has alleviated this issue to some extent, it also significantly increases the number of parameters required for fine-tuning and training time, introducing greater parameter redundancy. To address these challenges, we propose a method for allocating expert numbers based on parameter s"},"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":"2505.06272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T13:22:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8a9af1a62cca3f00b16c1ac9427f3a598c193256f93d73b78bb6f43aca0dbd1","abstract_canon_sha256":"95741ce6235876a006c66f9d8ac1dba19a180530c29c4115bf017ee9de5c132c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:06.412001Z","signature_b64":"DU/UvxhRpFgOIGdMXB24ulZGHu0GR/w+23oDnYklHdofQp2zLG4FWbr6Z0X43+11EUtmPkN2orFBfi8NtY2BBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b077629cb9d7dffb2a834fa4630dadf75cc6ff69300fccbb28bda9a50af792c8","last_reissued_at":"2026-07-05T11:01:06.411466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:06.411466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Sensitivity-Driven Expert Allocation Method in LoRA-MoE for Efficient Fine-Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boyu Diao, Junzhou Xu","submitted_at":"2025-05-06T13:22:46Z","abstract_excerpt":"As deep learning models expand, the pre-training-fine-tuning paradigm has become the standard approach for handling various downstream tasks. However, shared parameters can lead to diminished performance when dealing with complex datasets involving multiple tasks. While introducing Mixture-of-Experts (MoE) methods has alleviated this issue to some extent, it also significantly increases the number of parameters required for fine-tuning and training time, introducing greater parameter redundancy. To address these challenges, we propose a method for allocating expert numbers based on parameter s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06272","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/2505.06272/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":"2505.06272","created_at":"2026-07-05T11:01:06.411523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06272v1","created_at":"2026-07-05T11:01:06.411523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06272","created_at":"2026-07-05T11:01:06.411523+00:00"},{"alias_kind":"pith_short_12","alias_value":"WB3WFHFZ27P7","created_at":"2026-07-05T11:01:06.411523+00:00"},{"alias_kind":"pith_short_16","alias_value":"WB3WFHFZ27P7WKUD","created_at":"2026-07-05T11:01:06.411523+00:00"},{"alias_kind":"pith_short_8","alias_value":"WB3WFHFZ","created_at":"2026-07-05T11:01:06.411523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WB3WFHFZ27P7WKUDJ6SGGDNN65","json":"https://pith.science/pith/WB3WFHFZ27P7WKUDJ6SGGDNN65.json","graph_json":"https://pith.science/api/pith-number/WB3WFHFZ27P7WKUDJ6SGGDNN65/graph.json","events_json":"https://pith.science/api/pith-number/WB3WFHFZ27P7WKUDJ6SGGDNN65/events.json","paper":"https://pith.science/paper/WB3WFHFZ"},"agent_actions":{"view_html":"https://pith.science/pith/WB3WFHFZ27P7WKUDJ6SGGDNN65","download_json":"https://pith.science/pith/WB3WFHFZ27P7WKUDJ6SGGDNN65.json","view_paper":"https://pith.science/paper/WB3WFHFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06272&json=true","fetch_graph":"https://pith.science/api/pith-number/WB3WFHFZ27P7WKUDJ6SGGDNN65/graph.json","fetch_events":"https://pith.science/api/pith-number/WB3WFHFZ27P7WKUDJ6SGGDNN65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WB3WFHFZ27P7WKUDJ6SGGDNN65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WB3WFHFZ27P7WKUDJ6SGGDNN65/action/storage_attestation","attest_author":"https://pith.science/pith/WB3WFHFZ27P7WKUDJ6SGGDNN65/action/author_attestation","sign_citation":"https://pith.science/pith/WB3WFHFZ27P7WKUDJ6SGGDNN65/action/citation_signature","submit_replication":"https://pith.science/pith/WB3WFHFZ27P7WKUDJ6SGGDNN65/action/replication_record"}},"created_at":"2026-07-05T11:01:06.411523+00:00","updated_at":"2026-07-05T11:01:06.411523+00:00"}