{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EAIHDIULBZI4N7XSOYIUKYDE3R","short_pith_number":"pith:EAIHDIUL","schema_version":"1.0","canonical_sha256":"201071a28b0e51c6fef27611456064dc41cc4550d937099f6cc5fd9f5b22d137","source":{"kind":"arxiv","id":"2312.11875","version":3},"attestation_state":"computed","paper":{"title":"Sparse is Enough in Fine-tuning Pre-trained Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Du, Hai Zhao, Lefei Zhang, Weixi Song, Zuchao Li","submitted_at":"2023-12-19T06:06:30Z","abstract_excerpt":"With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation. Although PEFT has demonstrated effectiveness and been widely applied, the underlying principles are still unclear. In this paper, we adopt the PAC-Bayesian generalization error bound, viewing pre-training as a shift of prior distribution which leads to a tighter bound for generalization error. We validate this shift from the perspectives of oscilla"},"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":"2312.11875","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T06:06:30Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"63412c1e21be7cd313794a444918f24dc022d6af5364c9994b98a3f33115c37d","abstract_canon_sha256":"08a8180adb3287ccb8ae55176a0c01d592a1fd98cbe70ee9cec6adde172737c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:58.146811Z","signature_b64":"d11XiXe2+77L9PGKgXbapkCjfjjO07ihBaHQ198mxaZhnbuao+TcWjgPb6wVqFGl7RZG1hnAj0//d26eeyxAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"201071a28b0e51c6fef27611456064dc41cc4550d937099f6cc5fd9f5b22d137","last_reissued_at":"2026-07-05T08:28:58.146308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:58.146308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse is Enough in Fine-tuning Pre-trained Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Du, Hai Zhao, Lefei Zhang, Weixi Song, Zuchao Li","submitted_at":"2023-12-19T06:06:30Z","abstract_excerpt":"With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation. Although PEFT has demonstrated effectiveness and been widely applied, the underlying principles are still unclear. In this paper, we adopt the PAC-Bayesian generalization error bound, viewing pre-training as a shift of prior distribution which leads to a tighter bound for generalization error. We validate this shift from the perspectives of oscilla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11875","kind":"arxiv","version":3},"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/2312.11875/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":"2312.11875","created_at":"2026-07-05T08:28:58.146384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11875v3","created_at":"2026-07-05T08:28:58.146384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11875","created_at":"2026-07-05T08:28:58.146384+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAIHDIULBZI4","created_at":"2026-07-05T08:28:58.146384+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAIHDIULBZI4N7XS","created_at":"2026-07-05T08:28:58.146384+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAIHDIUL","created_at":"2026-07-05T08:28:58.146384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06297","citing_title":"FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R","json":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R.json","graph_json":"https://pith.science/api/pith-number/EAIHDIULBZI4N7XSOYIUKYDE3R/graph.json","events_json":"https://pith.science/api/pith-number/EAIHDIULBZI4N7XSOYIUKYDE3R/events.json","paper":"https://pith.science/paper/EAIHDIUL"},"agent_actions":{"view_html":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R","download_json":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R.json","view_paper":"https://pith.science/paper/EAIHDIUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11875&json=true","fetch_graph":"https://pith.science/api/pith-number/EAIHDIULBZI4N7XSOYIUKYDE3R/graph.json","fetch_events":"https://pith.science/api/pith-number/EAIHDIULBZI4N7XSOYIUKYDE3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/action/storage_attestation","attest_author":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/action/author_attestation","sign_citation":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/action/citation_signature","submit_replication":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/action/replication_record"}},"created_at":"2026-07-05T08:28:58.146384+00:00","updated_at":"2026-07-05T08:28:58.146384+00:00"}