{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TL6IPOFXSO3M6CV2UWQFZTR3QQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"20cd7237438600ad488b4bb07c4c15ef25db14c99f9802dc202bf0c5e5b31504","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-18T14:08:48Z","title_canon_sha256":"b9721e42e079bf1e682ce83974889b1b015edba25999d9b23a682dd2343800b1"},"schema_version":"1.0","source":{"id":"2402.11592","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11592","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11592v3","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11592","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"TL6IPOFXSO3M","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"TL6IPOFXSO3M6CV2","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"TL6IPOFX","created_at":"2026-07-05T08:24:02Z"}],"graph_snapshots":[{"event_id":"sha256:98d5182f464107327b41bd4e5079bf7b4a7f9da7d671d1ff15a9a5139a4c74c4","target":"graph","created_at":"2026-07-05T08:24:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.11592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the evolving landscape of natural language processing (NLP), fine-tuning pre-trained Large Language Models (LLMs) with first-order (FO) optimizers like SGD and Adam has become standard. Yet, as LLMs grow {in size}, the substantial memory overhead from back-propagation (BP) for FO gradient computation presents a significant challenge. Addressing this issue is crucial, especially for applications like on-device training where memory efficiency is paramount. This paper proposes a shift towards BP-free, zeroth-order (ZO) optimization as a solution for reducing memory costs during LLM fine-tunin","authors_text":"Jason D. Lee, Jiaxiang Li, Junyuan Hong, Mingyi Hong, Pingzhi Li, Pin-Yu Chen, Sijia Liu, Tianlong Chen, Wenqing Zheng, Wotao Yin, Yihua Zhang, Yimeng Zhang, Zhangyang Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-18T14:08:48Z","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11592","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:80a6a25902a42edfced8f3931c0409ddeec04e6d9ce3db2113a0bf2bdb5f6a14","target":"record","created_at":"2026-07-05T08:24:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"20cd7237438600ad488b4bb07c4c15ef25db14c99f9802dc202bf0c5e5b31504","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-18T14:08:48Z","title_canon_sha256":"b9721e42e079bf1e682ce83974889b1b015edba25999d9b23a682dd2343800b1"},"schema_version":"1.0","source":{"id":"2402.11592","kind":"arxiv","version":3}},"canonical_sha256":"9afc87b8b793b6cf0abaa5a05cce3b840f86d730f79c3d8a9bbcea1135c7aca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9afc87b8b793b6cf0abaa5a05cce3b840f86d730f79c3d8a9bbcea1135c7aca1","first_computed_at":"2026-07-05T08:24:02.148919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:02.148919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iwp0ONtf4g3P6suaW5fYzMgiz+yGP96YukjGBEGI9GFrIZf4NyK9KpQgwpD0rJo8ELRFh7z+VODHq3DwDtuFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:02.149405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11592","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80a6a25902a42edfced8f3931c0409ddeec04e6d9ce3db2113a0bf2bdb5f6a14","sha256:98d5182f464107327b41bd4e5079bf7b4a7f9da7d671d1ff15a9a5139a4c74c4"],"state_sha256":"a48752cb534453de4430737c313c9c8dcacaa3aa56203db31b86db9d666674f3"}