{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XCW5ZSSAESFMA5L3Z3OW4S2NC3","short_pith_number":"pith:XCW5ZSSA","schema_version":"1.0","canonical_sha256":"b8addcca40248ac0757bcedd6e4b4d16d2deb07f5a94fcc82ba610bd4f88f227","source":{"kind":"arxiv","id":"2504.14117","version":1},"attestation_state":"computed","paper":{"title":"PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Abdullah As Sami, Hafijur Raman, Md Kowsher, Md Shamol Ali, Md Shohanur Islam Sobuj, Nusrat Jahan Prottasha, Ozlem Ozmen Garibay, Shetu Mohanto, Tasfia Nuzhat, Upama Roy Chowdhury","submitted_at":"2025-04-19T00:33:16Z","abstract_excerpt":"Large models such as Large Language Models (LLMs) and Vision Language Models (VLMs) have transformed artificial intelligence, powering applications in natural language processing, computer vision, and multimodal learning. However, fully fine-tuning these models remains expensive, requiring extensive computational resources, memory, and task-specific data. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a promising solution that allows adapting large models to downstream tasks by updating only a small portion of parameters. This survey presents a comprehensive overview of PEFT techniques,"},"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":"2504.14117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T00:33:16Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9bfea36a4cdf9880ca8cf0ee666159080779f4792afdb7f48d79a95e343d02ec","abstract_canon_sha256":"c31a00b947aed63c87cf63a409bd1c1421d19d63d8f4e7479dd94ffae4d67082"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:11.203391Z","signature_b64":"G9Nvmulfuf+xjDihaJqb/LFN9/Z6NBNWuTNg85n0/kcgzpdWUP3T8cWCnWNjWNFEod5tv+8wC6zJTzHZ8SMaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8addcca40248ac0757bcedd6e4b4d16d2deb07f5a94fcc82ba610bd4f88f227","last_reissued_at":"2026-07-05T10:51:11.202885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:11.202885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Abdullah As Sami, Hafijur Raman, Md Kowsher, Md Shamol Ali, Md Shohanur Islam Sobuj, Nusrat Jahan Prottasha, Ozlem Ozmen Garibay, Shetu Mohanto, Tasfia Nuzhat, Upama Roy Chowdhury","submitted_at":"2025-04-19T00:33:16Z","abstract_excerpt":"Large models such as Large Language Models (LLMs) and Vision Language Models (VLMs) have transformed artificial intelligence, powering applications in natural language processing, computer vision, and multimodal learning. However, fully fine-tuning these models remains expensive, requiring extensive computational resources, memory, and task-specific data. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a promising solution that allows adapting large models to downstream tasks by updating only a small portion of parameters. This survey presents a comprehensive overview of PEFT techniques,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14117","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/2504.14117/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":"2504.14117","created_at":"2026-07-05T10:51:11.202948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14117v1","created_at":"2026-07-05T10:51:11.202948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14117","created_at":"2026-07-05T10:51:11.202948+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCW5ZSSAESFM","created_at":"2026-07-05T10:51:11.202948+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCW5ZSSAESFMA5L3","created_at":"2026-07-05T10:51:11.202948+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCW5ZSSA","created_at":"2026-07-05T10:51:11.202948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06918","citing_title":"LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2511.21285","citing_title":"PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCW5ZSSAESFMA5L3Z3OW4S2NC3","json":"https://pith.science/pith/XCW5ZSSAESFMA5L3Z3OW4S2NC3.json","graph_json":"https://pith.science/api/pith-number/XCW5ZSSAESFMA5L3Z3OW4S2NC3/graph.json","events_json":"https://pith.science/api/pith-number/XCW5ZSSAESFMA5L3Z3OW4S2NC3/events.json","paper":"https://pith.science/paper/XCW5ZSSA"},"agent_actions":{"view_html":"https://pith.science/pith/XCW5ZSSAESFMA5L3Z3OW4S2NC3","download_json":"https://pith.science/pith/XCW5ZSSAESFMA5L3Z3OW4S2NC3.json","view_paper":"https://pith.science/paper/XCW5ZSSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14117&json=true","fetch_graph":"https://pith.science/api/pith-number/XCW5ZSSAESFMA5L3Z3OW4S2NC3/graph.json","fetch_events":"https://pith.science/api/pith-number/XCW5ZSSAESFMA5L3Z3OW4S2NC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCW5ZSSAESFMA5L3Z3OW4S2NC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCW5ZSSAESFMA5L3Z3OW4S2NC3/action/storage_attestation","attest_author":"https://pith.science/pith/XCW5ZSSAESFMA5L3Z3OW4S2NC3/action/author_attestation","sign_citation":"https://pith.science/pith/XCW5ZSSAESFMA5L3Z3OW4S2NC3/action/citation_signature","submit_replication":"https://pith.science/pith/XCW5ZSSAESFMA5L3Z3OW4S2NC3/action/replication_record"}},"created_at":"2026-07-05T10:51:11.202948+00:00","updated_at":"2026-07-05T10:51:11.202948+00:00"}