{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OBHUWVR76YXXXGUD36M7ZXOQJZ","short_pith_number":"pith:OBHUWVR7","schema_version":"1.0","canonical_sha256":"704f4b563ff62f7b9a83df99fcddd04e413e8bbf815f3fe8a6b892c7a067c66d","source":{"kind":"arxiv","id":"2304.14999","version":1},"attestation_state":"computed","paper":{"title":"Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anirudh Jain, George Pu, Jihan Yin, Russell Kaplan","submitted_at":"2023-04-28T17:39:49Z","abstract_excerpt":"As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage of the model parameters, is currently the most popular method for adapting large language models (LLMs). Several PEFT techniques have recently been proposed with varying tradeoffs. We provide a comprehensive and uniform benchmark of various PEFT techniques across a representative LLM, the FLAN-T5 model, and evaluate model performance across different data sc"},"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":"2304.14999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T17:39:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6341d174240cf91f2577c446e3accbdcd882120935a4c89832f0d6b3c8641825","abstract_canon_sha256":"56cb79ae4a42e3e9ab8651141acaa3572e2cc35f2ce1930be14162175ea79a86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:23.149701Z","signature_b64":"Kta3cRuXSe8ZzbnGWXsjev3uuRQjoNEvDtU41GKpUMm8jMFb7GMgCQ1NDwgPANEY/EcK61rkG4gnJZhd1EHBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"704f4b563ff62f7b9a83df99fcddd04e413e8bbf815f3fe8a6b892c7a067c66d","last_reissued_at":"2026-07-05T06:05:23.149230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:23.149230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anirudh Jain, George Pu, Jihan Yin, Russell Kaplan","submitted_at":"2023-04-28T17:39:49Z","abstract_excerpt":"As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage of the model parameters, is currently the most popular method for adapting large language models (LLMs). Several PEFT techniques have recently been proposed with varying tradeoffs. We provide a comprehensive and uniform benchmark of various PEFT techniques across a representative LLM, the FLAN-T5 model, and evaluate model performance across different data sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14999","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/2304.14999/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":"2304.14999","created_at":"2026-07-05T06:05:23.149290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14999v1","created_at":"2026-07-05T06:05:23.149290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14999","created_at":"2026-07-05T06:05:23.149290+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBHUWVR76YXX","created_at":"2026-07-05T06:05:23.149290+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBHUWVR76YXXXGUD","created_at":"2026-07-05T06:05:23.149290+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBHUWVR7","created_at":"2026-07-05T06:05:23.149290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03209","citing_title":"DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBHUWVR76YXXXGUD36M7ZXOQJZ","json":"https://pith.science/pith/OBHUWVR76YXXXGUD36M7ZXOQJZ.json","graph_json":"https://pith.science/api/pith-number/OBHUWVR76YXXXGUD36M7ZXOQJZ/graph.json","events_json":"https://pith.science/api/pith-number/OBHUWVR76YXXXGUD36M7ZXOQJZ/events.json","paper":"https://pith.science/paper/OBHUWVR7"},"agent_actions":{"view_html":"https://pith.science/pith/OBHUWVR76YXXXGUD36M7ZXOQJZ","download_json":"https://pith.science/pith/OBHUWVR76YXXXGUD36M7ZXOQJZ.json","view_paper":"https://pith.science/paper/OBHUWVR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14999&json=true","fetch_graph":"https://pith.science/api/pith-number/OBHUWVR76YXXXGUD36M7ZXOQJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OBHUWVR76YXXXGUD36M7ZXOQJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBHUWVR76YXXXGUD36M7ZXOQJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBHUWVR76YXXXGUD36M7ZXOQJZ/action/storage_attestation","attest_author":"https://pith.science/pith/OBHUWVR76YXXXGUD36M7ZXOQJZ/action/author_attestation","sign_citation":"https://pith.science/pith/OBHUWVR76YXXXGUD36M7ZXOQJZ/action/citation_signature","submit_replication":"https://pith.science/pith/OBHUWVR76YXXXGUD36M7ZXOQJZ/action/replication_record"}},"created_at":"2026-07-05T06:05:23.149290+00:00","updated_at":"2026-07-05T06:05:23.149290+00:00"}