{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U6EERTYPBFZB3FSJLY4SFXOH7Z","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":"f85482f07f1319a8421df1e1a40a294245f9e3f20a2b00cdc604f8273238604b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T12:47:37Z","title_canon_sha256":"516b69c00e2c05ad79c972ddcf418df725800a294db47cb1efdb04cfc8e52874"},"schema_version":"1.0","source":{"id":"2410.09823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09823","created_at":"2026-07-05T09:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09823v1","created_at":"2026-07-05T09:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09823","created_at":"2026-07-05T09:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"U6EERTYPBFZB","created_at":"2026-07-05T09:20:06Z"},{"alias_kind":"pith_short_16","alias_value":"U6EERTYPBFZB3FSJ","created_at":"2026-07-05T09:20:06Z"},{"alias_kind":"pith_short_8","alias_value":"U6EERTYP","created_at":"2026-07-05T09:20:06Z"}],"graph_snapshots":[{"event_id":"sha256:65868b764b1e3882bd7179df2de4f789c8d1becad74dc892d0d56cc10753a701","target":"graph","created_at":"2026-07-05T09:20:06Z","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/2410.09823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning is powerful for adapting large language models to downstream tasks, but it often results in huge memory usages. A promising approach to mitigate this is using Zeroth-Order (ZO) optimization, which estimates gradients to replace First-Order (FO) gradient calculations, albeit with longer training time due to its stochastic nature. By revisiting the Memory-efficient ZO (MeZO) optimizer, we discover that the full-parameter perturbation and updating processes consume over 50% of its overall fine-tuning time cost. Based on these observations, we introduce a novel layer-wise sparse comput","authors_text":"Changxing Ding, Chao Xue, Fei Wang, Liang Ding, Li Shen, Ye Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T12:47:37Z","title":"Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09823","kind":"arxiv","version":1},"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":"sha256:48ee9b921724ff9811540a5b781c3104fc48a952306c179e6d3942a0acfd4f3e","target":"record","created_at":"2026-07-05T09:20:06Z","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":"f85482f07f1319a8421df1e1a40a294245f9e3f20a2b00cdc604f8273238604b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T12:47:37Z","title_canon_sha256":"516b69c00e2c05ad79c972ddcf418df725800a294db47cb1efdb04cfc8e52874"},"schema_version":"1.0","source":{"id":"2410.09823","kind":"arxiv","version":1}},"canonical_sha256":"a78848cf0f09721d96495e3922ddc7fe532985cbb4eb58f4248c5026b7935cc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a78848cf0f09721d96495e3922ddc7fe532985cbb4eb58f4248c5026b7935cc4","first_computed_at":"2026-07-05T09:20:06.662910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:06.662910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WTrrVRpk26QetU5FW+wlVe98n/NI/H/CHd1ZjRF9kn6fPWXLiZtTMUJIG+PIGZoRHrjhbjX9yRmcw6zHrzNGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:06.663365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48ee9b921724ff9811540a5b781c3104fc48a952306c179e6d3942a0acfd4f3e","sha256:65868b764b1e3882bd7179df2de4f789c8d1becad74dc892d0d56cc10753a701"],"state_sha256":"a6c4b8cb071fd8ec34230de694e01a0553971ff630f738dcead9167a5eb9a91d"}