{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BAS7PTPDKK6EJUTTQYADGCLNL4","short_pith_number":"pith:BAS7PTPD","schema_version":"1.0","canonical_sha256":"0825f7cde352bc44d273860033096d5f2515c647da53c33eebf2f5af6baba81e","source":{"kind":"arxiv","id":"2405.00361","version":2},"attestation_state":"computed","paper":{"title":"AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiahua Luo, Zefang Liu","submitted_at":"2024-05-01T07:33:43Z","abstract_excerpt":"We introduce AdaMoLE, a novel method for fine-tuning large language models (LLMs) through an Adaptive Mixture of Low-Rank Adaptation (LoRA) Experts. Moving beyond conventional methods that employ a static top-k strategy for activating experts, AdaMoLE dynamically adjusts the activation threshold using a dedicated threshold network, adaptively responding to the varying complexities of different tasks. By replacing a single LoRA in a layer with multiple LoRA experts and integrating a gating function with the threshold mechanism, AdaMoLE effectively selects and activates the most appropriate expe"},"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":"2405.00361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-01T07:33:43Z","cross_cats_sorted":[],"title_canon_sha256":"36013521ca0afb28af9ef0e1b0e25e0b91573b28f432fcedc7253cb0f3df07fe","abstract_canon_sha256":"649b47521ac8a2874e0af281ada01ebf86a0f9a0db700779af69b17849d26e7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:12.695716Z","signature_b64":"EodZRekFElCdnlRJWXegz+Mhx/vqgmSzJcFrK6uk/SnmsDOmoUqT7JNmqgNlCJo361XOsDd8Ou1kGl0deOPyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0825f7cde352bc44d273860033096d5f2515c647da53c33eebf2f5af6baba81e","last_reissued_at":"2026-07-05T08:54:12.695240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:12.695240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiahua Luo, Zefang Liu","submitted_at":"2024-05-01T07:33:43Z","abstract_excerpt":"We introduce AdaMoLE, a novel method for fine-tuning large language models (LLMs) through an Adaptive Mixture of Low-Rank Adaptation (LoRA) Experts. Moving beyond conventional methods that employ a static top-k strategy for activating experts, AdaMoLE dynamically adjusts the activation threshold using a dedicated threshold network, adaptively responding to the varying complexities of different tasks. By replacing a single LoRA in a layer with multiple LoRA experts and integrating a gating function with the threshold mechanism, AdaMoLE effectively selects and activates the most appropriate expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00361","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/2405.00361/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":"2405.00361","created_at":"2026-07-05T08:54:12.695300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00361v2","created_at":"2026-07-05T08:54:12.695300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00361","created_at":"2026-07-05T08:54:12.695300+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAS7PTPDKK6E","created_at":"2026-07-05T08:54:12.695300+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAS7PTPDKK6EJUTT","created_at":"2026-07-05T08:54:12.695300+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAS7PTPD","created_at":"2026-07-05T08:54:12.695300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26287","citing_title":"GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26183","citing_title":"LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07500","citing_title":"Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07111","citing_title":"Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07111","citing_title":"Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21335","citing_title":"Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAS7PTPDKK6EJUTTQYADGCLNL4","json":"https://pith.science/pith/BAS7PTPDKK6EJUTTQYADGCLNL4.json","graph_json":"https://pith.science/api/pith-number/BAS7PTPDKK6EJUTTQYADGCLNL4/graph.json","events_json":"https://pith.science/api/pith-number/BAS7PTPDKK6EJUTTQYADGCLNL4/events.json","paper":"https://pith.science/paper/BAS7PTPD"},"agent_actions":{"view_html":"https://pith.science/pith/BAS7PTPDKK6EJUTTQYADGCLNL4","download_json":"https://pith.science/pith/BAS7PTPDKK6EJUTTQYADGCLNL4.json","view_paper":"https://pith.science/paper/BAS7PTPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00361&json=true","fetch_graph":"https://pith.science/api/pith-number/BAS7PTPDKK6EJUTTQYADGCLNL4/graph.json","fetch_events":"https://pith.science/api/pith-number/BAS7PTPDKK6EJUTTQYADGCLNL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAS7PTPDKK6EJUTTQYADGCLNL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAS7PTPDKK6EJUTTQYADGCLNL4/action/storage_attestation","attest_author":"https://pith.science/pith/BAS7PTPDKK6EJUTTQYADGCLNL4/action/author_attestation","sign_citation":"https://pith.science/pith/BAS7PTPDKK6EJUTTQYADGCLNL4/action/citation_signature","submit_replication":"https://pith.science/pith/BAS7PTPDKK6EJUTTQYADGCLNL4/action/replication_record"}},"created_at":"2026-07-05T08:54:12.695300+00:00","updated_at":"2026-07-05T08:54:12.695300+00:00"}