{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PJ64HOC2ER7CND7FBSCAZBSH6P","short_pith_number":"pith:PJ64HOC2","schema_version":"1.0","canonical_sha256":"7a7dc3b85a247e268fe50c840c8647f3ca4417d459a9d6348e45c792f72d8c06","source":{"kind":"arxiv","id":"2606.14970","version":2},"attestation_state":"computed","paper":{"title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksandr Beznosikov, Daniil Medyakov, Dmitriy Bystrov, Dmitry Bylinkin","submitted_at":"2026-06-12T21:46:54Z","abstract_excerpt":"Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data. A major obstacle in large-scale fine-tuning is the memory overhead of backpropagation, which requires storing activations, gradients, and optimizer states. Zeroth-order (ZO) optimization offers a memory-efficient alternative, but its performance is highly sensitive to the stepsize and smoothing parameter, often requiring costly task-specific tuning. Parameter-free (PF) optimization addresses this issue by ada"},"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":"2606.14970","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-12T21:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"e0b7ca2723d762df38f575309f969365c01386f7d7c2bf39890b00c03e1d0989","abstract_canon_sha256":"3a0304ac0d5f3f4bdee048e774ae4504bbde55fa0d43d176dd19bcca8f72725e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:59.295353Z","signature_b64":"lXp2eocZeOfO+VzdCdAKpFOzf9zTJ6qGCkcDxqCCdFou7OEttaNDqag3PdIzzJprdaBqoGQM7CHgnaB5SnfbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a7dc3b85a247e268fe50c840c8647f3ca4417d459a9d6348e45c792f72d8c06","last_reissued_at":"2026-06-23T03:13:59.294865Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:59.294865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksandr Beznosikov, Daniil Medyakov, Dmitriy Bystrov, Dmitry Bylinkin","submitted_at":"2026-06-12T21:46:54Z","abstract_excerpt":"Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data. A major obstacle in large-scale fine-tuning is the memory overhead of backpropagation, which requires storing activations, gradients, and optimizer states. Zeroth-order (ZO) optimization offers a memory-efficient alternative, but its performance is highly sensitive to the stepsize and smoothing parameter, often requiring costly task-specific tuning. Parameter-free (PF) optimization addresses this issue by ada"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.14970","kind":"arxiv","version":2},"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/2606.14970/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":"2606.14970","created_at":"2026-06-23T03:13:59.294922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.14970v2","created_at":"2026-06-23T03:13:59.294922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.14970","created_at":"2026-06-23T03:13:59.294922+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJ64HOC2ER7C","created_at":"2026-06-23T03:13:59.294922+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJ64HOC2ER7CND7F","created_at":"2026-06-23T03:13:59.294922+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJ64HOC2","created_at":"2026-06-23T03:13:59.294922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P","json":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P.json","graph_json":"https://pith.science/api/pith-number/PJ64HOC2ER7CND7FBSCAZBSH6P/graph.json","events_json":"https://pith.science/api/pith-number/PJ64HOC2ER7CND7FBSCAZBSH6P/events.json","paper":"https://pith.science/paper/PJ64HOC2"},"agent_actions":{"view_html":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P","download_json":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P.json","view_paper":"https://pith.science/paper/PJ64HOC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.14970&json=true","fetch_graph":"https://pith.science/api/pith-number/PJ64HOC2ER7CND7FBSCAZBSH6P/graph.json","fetch_events":"https://pith.science/api/pith-number/PJ64HOC2ER7CND7FBSCAZBSH6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/action/storage_attestation","attest_author":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/action/author_attestation","sign_citation":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/action/citation_signature","submit_replication":"https://pith.science/pith/PJ64HOC2ER7CND7FBSCAZBSH6P/action/replication_record"}},"created_at":"2026-06-23T03:13:59.294922+00:00","updated_at":"2026-06-23T03:13:59.294922+00:00"}