{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PSQOCR56IDO2XCIRW3QUT2XE4L","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":"301b1699904a1871ec5625ae9cd9b6f3a354bcefd6f8d89423291b3976d3c490","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-08T08:27:15Z","title_canon_sha256":"a6c79fe0a2fcd4aa0832b90620fc4b827c90328a1f228d22484b1557c5e4428d"},"schema_version":"1.0","source":{"id":"2601.04710","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.04710","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2601.04710v2","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.04710","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"PSQOCR56IDO2","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"PSQOCR56IDO2XCIR","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"PSQOCR56","created_at":"2026-06-11T01:09:26Z"}],"graph_snapshots":[{"event_id":"sha256:e7095e3182eb498ef05f00b4e8b65a9b6c36d39bad2a1760db0be9e7692a56cb","target":"graph","created_at":"2026-06-11T01:09:26Z","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/2601.04710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large language models (LLMs) achieves strong performance but is often limited by the memory overhead of backpropagation. Zeroth-order (ZO) optimization avoids this overhead by estimating gradients through forward passes alone, yet it typically converges slowly because random Gaussian perturbations yield high-variance gradient estimates in high-dimensional parameter spaces. In this paper, we propose a plug-and-play framework that turns random perturbations into more effective descent directions. The key idea is to draw a small pool of candidate perturbations, evaluate their loss val","authors_text":"Feihu Jin, Shipeng Cen, Ying Tan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-08T08:27:15Z","title":"Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.04710","kind":"arxiv","version":2},"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":"sha256:7aabf2644e6771cd953c7250bdb0f6e267733ddf0e0ffe84b36339a541e062ef","target":"record","created_at":"2026-06-11T01:09:26Z","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":"301b1699904a1871ec5625ae9cd9b6f3a354bcefd6f8d89423291b3976d3c490","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-08T08:27:15Z","title_canon_sha256":"a6c79fe0a2fcd4aa0832b90620fc4b827c90328a1f228d22484b1557c5e4428d"},"schema_version":"1.0","source":{"id":"2601.04710","kind":"arxiv","version":2}},"canonical_sha256":"7ca0e147be40ddab8911b6e149eae4e2e07d550a64d93d9053db97b9054be7a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ca0e147be40ddab8911b6e149eae4e2e07d550a64d93d9053db97b9054be7a5","first_computed_at":"2026-06-11T01:09:26.074595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:26.074595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8NJ9dPtlJCeyEhKYyJSSdZYdCHy0BEc94ZKizV5tQIqupn9Z1VnZC5d1SvHg+qBUwHY6WwwyVEknfdAsx0HMCg==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:26.075604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.04710","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7aabf2644e6771cd953c7250bdb0f6e267733ddf0e0ffe84b36339a541e062ef","sha256:e7095e3182eb498ef05f00b4e8b65a9b6c36d39bad2a1760db0be9e7692a56cb"],"state_sha256":"18b7101106956dedf869044ca7752f161ad78da1dc1ee288acc8f89073b83cc6"}