{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZMSVW6DHOMKRULU5OZ7H3FDP4E","short_pith_number":"pith:ZMSVW6DH","schema_version":"1.0","canonical_sha256":"cb255b786773151a2e9d767e7d946fe108b47c58de7058a4d2eaee17659e0611","source":{"kind":"arxiv","id":"2411.16775","version":1},"attestation_state":"computed","paper":{"title":"Parameter Efficient Instruction Tuning: An Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pengfei He","submitted_at":"2024-11-25T07:06:09Z","abstract_excerpt":"Instruction tuning has become an important step for finetuning pretrained language models to better follow human instructions and generalize on various tasks. Nowadays, pretrained language models become increasingly larger, and full parameter finetuning is overwhelmingly costly. Therefore, Parameter Efficient Finetuning (PEFT) has arisen as a cost-effective practice for instruction tuning because of significantly smaller computational, memory, and storage cost compared to full finetuning. Despite their widespread adaptations, the vast hyperparameter spaces, the number of PEFT methods, the diff"},"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":"2411.16775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T07:06:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"884603119e02ab8d4b547bd370bd6a7d70ef816abb40970a958cb50cd07da3cf","abstract_canon_sha256":"dddaa03d6788346ebe03932d8310fa141f43d0fe5b2ab8c4f9311c773dce0b2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:22.969421Z","signature_b64":"ltJ7ia8+2sPLfUO3ohs8uP3QKxRYdT18kc8Ye5tH8ON33zfDn0ydi7/B5+PWJ5TF5sa5zsAReNx0ymLJVrInAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb255b786773151a2e9d767e7d946fe108b47c58de7058a4d2eaee17659e0611","last_reissued_at":"2026-07-05T09:40:22.969060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:22.969060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter Efficient Instruction Tuning: An Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pengfei He","submitted_at":"2024-11-25T07:06:09Z","abstract_excerpt":"Instruction tuning has become an important step for finetuning pretrained language models to better follow human instructions and generalize on various tasks. Nowadays, pretrained language models become increasingly larger, and full parameter finetuning is overwhelmingly costly. Therefore, Parameter Efficient Finetuning (PEFT) has arisen as a cost-effective practice for instruction tuning because of significantly smaller computational, memory, and storage cost compared to full finetuning. Despite their widespread adaptations, the vast hyperparameter spaces, the number of PEFT methods, the diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16775","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/2411.16775/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":"2411.16775","created_at":"2026-07-05T09:40:22.969116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16775v1","created_at":"2026-07-05T09:40:22.969116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16775","created_at":"2026-07-05T09:40:22.969116+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMSVW6DHOMKR","created_at":"2026-07-05T09:40:22.969116+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMSVW6DHOMKRULU5","created_at":"2026-07-05T09:40:22.969116+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMSVW6DH","created_at":"2026-07-05T09:40:22.969116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22355","citing_title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZMSVW6DHOMKRULU5OZ7H3FDP4E","json":"https://pith.science/pith/ZMSVW6DHOMKRULU5OZ7H3FDP4E.json","graph_json":"https://pith.science/api/pith-number/ZMSVW6DHOMKRULU5OZ7H3FDP4E/graph.json","events_json":"https://pith.science/api/pith-number/ZMSVW6DHOMKRULU5OZ7H3FDP4E/events.json","paper":"https://pith.science/paper/ZMSVW6DH"},"agent_actions":{"view_html":"https://pith.science/pith/ZMSVW6DHOMKRULU5OZ7H3FDP4E","download_json":"https://pith.science/pith/ZMSVW6DHOMKRULU5OZ7H3FDP4E.json","view_paper":"https://pith.science/paper/ZMSVW6DH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16775&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMSVW6DHOMKRULU5OZ7H3FDP4E/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMSVW6DHOMKRULU5OZ7H3FDP4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMSVW6DHOMKRULU5OZ7H3FDP4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMSVW6DHOMKRULU5OZ7H3FDP4E/action/storage_attestation","attest_author":"https://pith.science/pith/ZMSVW6DHOMKRULU5OZ7H3FDP4E/action/author_attestation","sign_citation":"https://pith.science/pith/ZMSVW6DHOMKRULU5OZ7H3FDP4E/action/citation_signature","submit_replication":"https://pith.science/pith/ZMSVW6DHOMKRULU5OZ7H3FDP4E/action/replication_record"}},"created_at":"2026-07-05T09:40:22.969116+00:00","updated_at":"2026-07-05T09:40:22.969116+00:00"}