{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5ITIMXHNA6T7356FR6WYBRGUQP","short_pith_number":"pith:5ITIMXHN","schema_version":"1.0","canonical_sha256":"ea26865ced07a7fdf7c58fad80c4d483cf0ecd44f509a60d870a43d8aa1c859e","source":{"kind":"arxiv","id":"2306.07967","version":2},"attestation_state":"computed","paper":{"title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Arnav Chavan, Deepak Gupta, Eric Xing, Zhiqiang Shen, Zhuang Liu","submitted_at":"2023-06-13T17:59:32Z","abstract_excerpt":"We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks. Enhancing Low-Rank Adaptation (LoRA), GLoRA employs a generalized prompt module to optimize pre-trained model weights and adjust intermediate activations, providing more flexibility and capability across diverse tasks and datasets. Moreover, GLoRA facilitates efficient parameter adaptation by employing a scalable, modular, layer-wise structure search that learns individual adapter of each layer. Originating from a unified mathematical formulation, GLoRA exhibits strong transfer learni"},"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":"2306.07967","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T17:59:32Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"00e358430f017bf516324ac83cd07583783440fb3686bfea2ebf0cf15ec5b0e2","abstract_canon_sha256":"4f0218d8a6e9435cea836376b586c6c452aa699cb489cd5bbb13b1a25eeffcf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:02.632286Z","signature_b64":"k5ifReZserlD+giOlDkDaMCHWkS4A6POlm+p65YxMvKZIKc5P9uueoswHMv7iZPPjWqIIBLOgZuDCKSroOWgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea26865ced07a7fdf7c58fad80c4d483cf0ecd44f509a60d870a43d8aa1c859e","last_reissued_at":"2026-07-05T07:01:02.631713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:02.631713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Arnav Chavan, Deepak Gupta, Eric Xing, Zhiqiang Shen, Zhuang Liu","submitted_at":"2023-06-13T17:59:32Z","abstract_excerpt":"We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks. Enhancing Low-Rank Adaptation (LoRA), GLoRA employs a generalized prompt module to optimize pre-trained model weights and adjust intermediate activations, providing more flexibility and capability across diverse tasks and datasets. Moreover, GLoRA facilitates efficient parameter adaptation by employing a scalable, modular, layer-wise structure search that learns individual adapter of each layer. Originating from a unified mathematical formulation, GLoRA exhibits strong transfer learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07967","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/2306.07967/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":"2306.07967","created_at":"2026-07-05T07:01:02.631780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07967v2","created_at":"2026-07-05T07:01:02.631780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07967","created_at":"2026-07-05T07:01:02.631780+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ITIMXHNA6T7","created_at":"2026-07-05T07:01:02.631780+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ITIMXHNA6T7356F","created_at":"2026-07-05T07:01:02.631780+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ITIMXHN","created_at":"2026-07-05T07:01:02.631780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08565","citing_title":"EinSort: Sorting is All We Need for Tensorizing LLM","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01947","citing_title":"Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10009","citing_title":"Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12686","citing_title":"BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ITIMXHNA6T7356FR6WYBRGUQP","json":"https://pith.science/pith/5ITIMXHNA6T7356FR6WYBRGUQP.json","graph_json":"https://pith.science/api/pith-number/5ITIMXHNA6T7356FR6WYBRGUQP/graph.json","events_json":"https://pith.science/api/pith-number/5ITIMXHNA6T7356FR6WYBRGUQP/events.json","paper":"https://pith.science/paper/5ITIMXHN"},"agent_actions":{"view_html":"https://pith.science/pith/5ITIMXHNA6T7356FR6WYBRGUQP","download_json":"https://pith.science/pith/5ITIMXHNA6T7356FR6WYBRGUQP.json","view_paper":"https://pith.science/paper/5ITIMXHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07967&json=true","fetch_graph":"https://pith.science/api/pith-number/5ITIMXHNA6T7356FR6WYBRGUQP/graph.json","fetch_events":"https://pith.science/api/pith-number/5ITIMXHNA6T7356FR6WYBRGUQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ITIMXHNA6T7356FR6WYBRGUQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ITIMXHNA6T7356FR6WYBRGUQP/action/storage_attestation","attest_author":"https://pith.science/pith/5ITIMXHNA6T7356FR6WYBRGUQP/action/author_attestation","sign_citation":"https://pith.science/pith/5ITIMXHNA6T7356FR6WYBRGUQP/action/citation_signature","submit_replication":"https://pith.science/pith/5ITIMXHNA6T7356FR6WYBRGUQP/action/replication_record"}},"created_at":"2026-07-05T07:01:02.631780+00:00","updated_at":"2026-07-05T07:01:02.631780+00:00"}