{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5IVXKLYKVYC3F6MVWFWFR6QVGW","short_pith_number":"pith:5IVXKLYK","schema_version":"1.0","canonical_sha256":"ea2b752f0aae05b2f995b16c58fa1535a16509936664f53f42b82d4c04a1f414","source":{"kind":"arxiv","id":"2408.09856","version":1},"attestation_state":"computed","paper":{"title":"TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Jiang, Haoyuan Li, Jiang Liu, Juncheng Li, Siliang Tang, Tianwei Lin, Wanggui He, Wenqiao Zhang, Yang Dai, Yueting Zhuang, Zhaocheng Li, Zhelun Yu","submitted_at":"2024-08-19T09:58:53Z","abstract_excerpt":"While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have effectively addressed GPU memory constraints during fine-tuning, their performance often falls short, especially in multidimensional task scenarios. To address this issue, one straightforward solution is to introduce task-specific LoRA modules as domain experts, leveraging the modeling of multiple experts' capabilities and thus enhancing the general capability of multi-task learning. Despite promising, these additional components often add complexity to the training and inference process, contravening the efficient characteriz"},"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":"2408.09856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T09:58:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af975e35515bd5cdc8de92160e1c6ce6d33a633c00d246934bd3f235ffc66af3","abstract_canon_sha256":"a7c94517d3a8d7d907cd4cb8158533425020b4c41de5942ce2f2e38fe5b61d7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:38.300388Z","signature_b64":"CKp/iEEsRxIbORrbjW7ZTXsP6weeVK4nNn6SVyjWdmanKFtuSZE0Etr7UtLDEy37sh51AmtA8N8KsV09YIq0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea2b752f0aae05b2f995b16c58fa1535a16509936664f53f42b82d4c04a1f414","last_reissued_at":"2026-07-05T08:56:38.299785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:38.299785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Jiang, Haoyuan Li, Jiang Liu, Juncheng Li, Siliang Tang, Tianwei Lin, Wanggui He, Wenqiao Zhang, Yang Dai, Yueting Zhuang, Zhaocheng Li, Zhelun Yu","submitted_at":"2024-08-19T09:58:53Z","abstract_excerpt":"While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have effectively addressed GPU memory constraints during fine-tuning, their performance often falls short, especially in multidimensional task scenarios. To address this issue, one straightforward solution is to introduce task-specific LoRA modules as domain experts, leveraging the modeling of multiple experts' capabilities and thus enhancing the general capability of multi-task learning. Despite promising, these additional components often add complexity to the training and inference process, contravening the efficient characteriz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09856","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/2408.09856/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":"2408.09856","created_at":"2026-07-05T08:56:38.299866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09856v1","created_at":"2026-07-05T08:56:38.299866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09856","created_at":"2026-07-05T08:56:38.299866+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IVXKLYKVYC3","created_at":"2026-07-05T08:56:38.299866+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IVXKLYKVYC3F6MV","created_at":"2026-07-05T08:56:38.299866+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IVXKLYK","created_at":"2026-07-05T08:56:38.299866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.04300","citing_title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IVXKLYKVYC3F6MVWFWFR6QVGW","json":"https://pith.science/pith/5IVXKLYKVYC3F6MVWFWFR6QVGW.json","graph_json":"https://pith.science/api/pith-number/5IVXKLYKVYC3F6MVWFWFR6QVGW/graph.json","events_json":"https://pith.science/api/pith-number/5IVXKLYKVYC3F6MVWFWFR6QVGW/events.json","paper":"https://pith.science/paper/5IVXKLYK"},"agent_actions":{"view_html":"https://pith.science/pith/5IVXKLYKVYC3F6MVWFWFR6QVGW","download_json":"https://pith.science/pith/5IVXKLYKVYC3F6MVWFWFR6QVGW.json","view_paper":"https://pith.science/paper/5IVXKLYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09856&json=true","fetch_graph":"https://pith.science/api/pith-number/5IVXKLYKVYC3F6MVWFWFR6QVGW/graph.json","fetch_events":"https://pith.science/api/pith-number/5IVXKLYKVYC3F6MVWFWFR6QVGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IVXKLYKVYC3F6MVWFWFR6QVGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IVXKLYKVYC3F6MVWFWFR6QVGW/action/storage_attestation","attest_author":"https://pith.science/pith/5IVXKLYKVYC3F6MVWFWFR6QVGW/action/author_attestation","sign_citation":"https://pith.science/pith/5IVXKLYKVYC3F6MVWFWFR6QVGW/action/citation_signature","submit_replication":"https://pith.science/pith/5IVXKLYKVYC3F6MVWFWFR6QVGW/action/replication_record"}},"created_at":"2026-07-05T08:56:38.299866+00:00","updated_at":"2026-07-05T08:56:38.299866+00:00"}