{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OJ5FCSUWPLEK4JOM23I5M4745K","short_pith_number":"pith:OJ5FCSUW","schema_version":"1.0","canonical_sha256":"727a514a967ac8ae25ccd6d1d673fcea9275f8bc8b7949e27d28e0b594ddf380","source":{"kind":"arxiv","id":"2410.07698","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kun Yuan, Liyuan Cao, Yiming Chen, Yuan Zhang, Zaiwen Wen","submitted_at":"2024-10-10T08:10:53Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) significantly reduces memory costs when adapting large language models (LLMs) for downstream applications. However, traditional first-order (FO) fine-tuning algorithms incur substantial memory overhead due to the need to store activation values for back-propagation during gradient computation, particularly in long-context fine-tuning tasks. Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values, thus eliminating the need for activation storage. Nevertheless, existing ZO methods str"},"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":"2410.07698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T08:10:53Z","cross_cats_sorted":[],"title_canon_sha256":"b687269cf030c8a85326cf7f44d70bdcb368d6f556d7319c8e521f54430c90fa","abstract_canon_sha256":"e78ddef9d8b2a377676e1c3b430863beee7f721e09bcb74ec9e46be713d8b6da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:42.217752Z","signature_b64":"DMYlM1zFIjl8yrnu8WFV5/Tv8wRZVPP6OqXWZxEDnE0XuTRx8DLK19Dop2oOdZb/3lWKXccar98Mdg/aqwaiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"727a514a967ac8ae25ccd6d1d673fcea9275f8bc8b7949e27d28e0b594ddf380","last_reissued_at":"2026-07-05T09:18:42.217228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:42.217228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kun Yuan, Liyuan Cao, Yiming Chen, Yuan Zhang, Zaiwen Wen","submitted_at":"2024-10-10T08:10:53Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) significantly reduces memory costs when adapting large language models (LLMs) for downstream applications. However, traditional first-order (FO) fine-tuning algorithms incur substantial memory overhead due to the need to store activation values for back-propagation during gradient computation, particularly in long-context fine-tuning tasks. Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values, thus eliminating the need for activation storage. Nevertheless, existing ZO methods str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07698","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/2410.07698/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":"2410.07698","created_at":"2026-07-05T09:18:42.217286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07698v1","created_at":"2026-07-05T09:18:42.217286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07698","created_at":"2026-07-05T09:18:42.217286+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJ5FCSUWPLEK","created_at":"2026-07-05T09:18:42.217286+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJ5FCSUWPLEK4JOM","created_at":"2026-07-05T09:18:42.217286+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJ5FCSUW","created_at":"2026-07-05T09:18:42.217286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14970","citing_title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05516","citing_title":"Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09034","citing_title":"Accelerating Zeroth-Order Spectral Optimization with Partial Orthogonalization from Power Iteration","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15113","citing_title":"Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18993","citing_title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09034","citing_title":"Accelerating Zeroth-Order Spectral Optimization with Partial Orthogonalization from Power Iteration","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00650","citing_title":"AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJ5FCSUWPLEK4JOM23I5M4745K","json":"https://pith.science/pith/OJ5FCSUWPLEK4JOM23I5M4745K.json","graph_json":"https://pith.science/api/pith-number/OJ5FCSUWPLEK4JOM23I5M4745K/graph.json","events_json":"https://pith.science/api/pith-number/OJ5FCSUWPLEK4JOM23I5M4745K/events.json","paper":"https://pith.science/paper/OJ5FCSUW"},"agent_actions":{"view_html":"https://pith.science/pith/OJ5FCSUWPLEK4JOM23I5M4745K","download_json":"https://pith.science/pith/OJ5FCSUWPLEK4JOM23I5M4745K.json","view_paper":"https://pith.science/paper/OJ5FCSUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07698&json=true","fetch_graph":"https://pith.science/api/pith-number/OJ5FCSUWPLEK4JOM23I5M4745K/graph.json","fetch_events":"https://pith.science/api/pith-number/OJ5FCSUWPLEK4JOM23I5M4745K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJ5FCSUWPLEK4JOM23I5M4745K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJ5FCSUWPLEK4JOM23I5M4745K/action/storage_attestation","attest_author":"https://pith.science/pith/OJ5FCSUWPLEK4JOM23I5M4745K/action/author_attestation","sign_citation":"https://pith.science/pith/OJ5FCSUWPLEK4JOM23I5M4745K/action/citation_signature","submit_replication":"https://pith.science/pith/OJ5FCSUWPLEK4JOM23I5M4745K/action/replication_record"}},"created_at":"2026-07-05T09:18:42.217286+00:00","updated_at":"2026-07-05T09:18:42.217286+00:00"}